Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
⚠ Concerns:(1) Has not raced in 33 days. (2) Poor record at this distance (0 wins from 5 recent starts). (3) Trip note from last race: Chased 3w turn; tired. (4) Speed figures are highly erratic over last 5 starts (σ = 18.6 pts: [52, 47, 60, 72, 22]) — unpredictable performer. (5) 0 wins from 6 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 60 (4/7) Mod2(W): 40 (4/7) Mod3(W): 67 (4/7) Mod1-LS: 0 Mod2-LS: 45 (4/7) Mod3-LS: 36 (7/7) Mod4(Form): 47 (4/7) Win Prob: 50.6% Value Score: 4.69 ★ ML: 6.00 (5/1) Overlay %: 2.25 Fair Odds: 6.67 (6/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | C | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | F |
| Early Pace | A | C |
| Mid Pace | A | C |
| Late Pace | F | D |
| Finish Pos | D | F |
| Dirt Speed | A | C |
| Turf Speed | C | D |
| Distance Speed | D | C |
| Trainer Effectiveness | D | F |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | A | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | F |
| Early Pace | A | B |
| Mid Pace | A | C |
| Late Pace | D | D |
| Sprint FPS | A | A |
| Route FPS | A | C |
| Trainer Effectiveness | D | F |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | A | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | F |
| Early Pace | A | B |
| Mid Pace | A | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Carries 5 lbs less than field median (120 lbs vs median 125 lbs). (2) Had documented trouble last race (codes: ['B', 'D', 'L', 'S', 'T', 'U']) yet still finished 2nd — a clean trip today sets up a form reversal. (3) Averages 53.5 speed pts in today's distance/surface configuration vs 43.5 in other configs (8 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Repeatedly beaten at this class level (3 of last 5 starts). (2) Poor record at this distance (0 wins from 9 recent starts). (3) Poor record at this track (0 wins from 9 starts). (4) Trip note from last race: Stumbled; late energy. (5) No workout in last 30 days despite 19 days since last race. (6) 0 wins from 9 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 70 (3/7) Mod2(W): 64 (3/7) Mod3(W): 84 (3/7) Mod1-LS: 25 (7/7) Mod2-LS: 70 (3/7) Mod3-LS: 72 (4/7) Mod4(Form): 81 (2/7) Win Prob: 58% Value Score: 3.07 ★ ML: 3.00 (2/1) Overlay %: -5.30 Fair Odds: 6.37 (5/1) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | F |
| Early Pace | B | D |
| Mid Pace | D | D |
| Late Pace | B | D |
| Finish Pos | C | F |
| Dirt Speed | D | D |
| Turf Speed | A | C |
| Distance Speed | B | C |
| Trainer Effectiveness | C | D |
| Jockey Effectiveness | B | D |
| 3rd Party Ratings | C | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | F |
| Early Pace | B | D |
| Mid Pace | C | D |
| Late Pace | B | C |
| Sprint FPS | C | D |
| Route FPS | D | D |
| Trainer Effectiveness | C | D |
| Jockey Effectiveness | B | D |
| 3rd Party Ratings | C | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | F |
| Early Pace | A | C |
| Mid Pace | C | D |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Speed average (59) well above field median (52). (2) Hot trainer - high ITM rate (43%). (3) Late pace significantly above field median (LP: 70 vs field 64). (4) Had documented trouble last race (codes: ['B', 'D', 'F', 'S', 'T']) yet still finished 4th — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Poor record at this distance (0 wins from 10 recent starts). (2) Poor record at this track (0 wins from 10 starts). (3) Trip note from last race: Far back; inside trip. (4) Consistently runs wide at the first call (3 of last 5 starts). (5) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 84 (2/7) Mod2(W): 75 (2/7) Mod3(W): 100 (1/7) Mod1-LS: 28 (6/7) Mod2-LS: 83 (2/7) Mod3-LS: 0 Mod4(Form): 68 (3/7) Win Prob: 55.4% Value Score: 3.67 ★ ML: 4.00 (3/1) Overlay %: -0.92 Fair Odds: 6.05 (5/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | D |
| Early Pace | C | D |
| Mid Pace | B | D |
| Late Pace | A | C |
| Finish Pos | A | C |
| Dirt Speed | B | C |
| Turf Speed | C | D |
| Distance Speed | A | B |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | C | D |
| 3rd Party Ratings | A | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | D |
| Early Pace | C | D |
| Mid Pace | B | D |
| Late Pace | A | B |
| Sprint FPS | D | D |
| Route FPS | B | D |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | C | D |
| 3rd Party Ratings | A | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | D |
| Early Pace | B | D |
| Mid Pace | B | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Hot jockey — high ITM rate (41%). (2) Late pace significantly above field median (LP: 70 vs field 64). (3) Fourth race back from a 106-day layoff — often the peak fitness race. (4) Career-best figure (63) buried in races 4–10 back — 10 pts above race median and 5 pts above recent form — market has forgotten the peak effort.
⚠ Concerns:(1) Poor record at this distance (0 wins from 10 recent starts). (2) Poor record at this track (0 wins from 20 starts). (3) Trip note from last race: Never a factor. (4) Cold trainer - low ITM rate (6%). (5) 0 wins from post 4 in 4 recent starts. (6) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 12 (7/7) Mod2(W): 9 (7/7) Mod3(W): 4 (7/7) Mod1-LS: 56 (3/7) Mod2-LS: 16 (7/7) Mod3-LS: 100 (1/7) Mod4(Form): 1 (7/7) Win Prob: 18.6% Value Score: 3.95 ★ ML: 15.00 (15/1) Overlay %: 6.12 Fair Odds: 8.23 (7/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | D |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | F |
| Early Pace | D | D |
| Mid Pace | C | D |
| Late Pace | A | C |
| Finish Pos | C | F |
| Dirt Speed | B | C |
| Turf Speed | C | D |
| Distance Speed | B | C |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | A | C |
| 3rd Party Ratings | D | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | D |
| Early Pace | D | D |
| Mid Pace | D | D |
| Late Pace | A | B |
| Sprint FPS | F | D |
| Route FPS | F | D |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | A | C |
| 3rd Party Ratings | D | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | F |
| Early Pace | C | D |
| Mid Pace | B | D |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 124-day layoff with a recent workout. (2) Significantly better on off tracks (off: 56 vs fast: 48). (3) Hot trainer - high ITM rate (49%). (4) Big last-race effort (56) — 14 pts above recent average. (5) Trainer 'SERVIS J TYLER' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now.
⚠ Concerns:(1) Has not raced in 124 days. (2) Speed average (46) well below field median (52). (3) Trip note from last race: Wide; no factor. (4) Last race was career-best speed (56) — bounce risk after peak effort. (5) Dropping in class in consecutive starts ($40,000 → $16,000 → $10,000).
Mod1(W): 0 Mod2(W): 0 Mod3(W): 0 Mod1-LS: 45 (4/7) Mod2-LS: 0 Mod3-LS: 91 (2/7) Mod4(Form): 0 Win Prob: 14.5% Value Score: 3.08 ★ ML: 15.00 (15/1) Overlay %: 5.60 Fair Odds: 8.69 (8/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | D |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | F |
| Early Pace | B | D |
| Mid Pace | B | D |
| Late Pace | D | D |
| Finish Pos | F | F |
| Dirt Speed | D | D |
| Turf Speed | C | D |
| Distance Speed | D | C |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | B | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | F |
| Early Pace | B | C |
| Mid Pace | B | D |
| Late Pace | F | F |
| Sprint FPS | B | D |
| Route FPS | D | D |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | B | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | F |
| Early Pace | D | D |
| Mid Pace | D | D |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 171-day layoff with a recent workout. (2) Dropping in class today ($15,000 → $10,000). (3) Hot trainer - high ITM rate (59%). (4) Strong trainer/jockey combo - 28 wins from 67 starts (42%). (5) Career-best speed figure (38) recorded in last 1-2 starts — peaking form. (6) Equipment change today (code: 1). (7) Hot jockey — high ITM rate (52%). (8) 3 workouts in last 30 days — horse appears sharp and fit. (9) Consistent workout spacing (9, 8 days) — disciplined training regimen. (10) Dropping in class ($10,000 vs last $15,000) after a 171-day freshening — trainer setup-for-win angle. (11) Carries 5 lbs less than field median (120 lbs vs median 125 lbs). (12) Trainer 'PINO MICHAEL V' has 4 horses in today's card all showing last-race improvement — barn appears sharp right now. (13) Had documented trouble last race (codes: ['B', 'D', 'F', 'L', 'O', 'S', 'T', 'U']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 171 days. (2) Was claimed from its most recent race - new connections. (3) Speed average (38) well below field median (52). (4) Limited experience at today's distance (1 start). (5) Unproven on dirt surface (1 start). (6) Trip note from last race: Bumped; off bit slow.
Mod1(W): 100 (1/7) Mod2(W): 100 (1/7) Mod3(W): 98 (2/7) Mod1-LS: 82 (2/7) Mod2-LS: 100 (1/7) Mod3-LS: 59 (6/7) Mod4(Form): 100 (1/7) Win Prob: 74.2% Value Score: 2.55 ★ ML: 1.60 (3/5) Overlay %: -15.60 Fair Odds: 6.44 (5/1) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | F | F |
| Early Pace | F | F |
| Mid Pace | F | D |
| Late Pace | D | D |
| Finish Pos | A | B |
| Dirt Speed | F | D |
| Turf Speed | C | D |
| Distance Speed | F | D |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | D | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | F |
| Early Pace | D | D |
| Mid Pace | D | D |
| Late Pace | C | D |
| Sprint FPS | D | D |
| Route FPS | C | D |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | D | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | F |
| Early Pace | F | F |
| Mid Pace | F | F |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Hot jockey — high ITM rate (37%). (2) Trainer 'GUERRERO MELECIO SALDANA' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (3) Had documented trouble last race (codes: ['D', 'L', 'S', 'T', 'V']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Poor record at this distance (0 wins from 5 recent starts). (2) Poor record at this track (0 wins from 15 starts). (3) Trip note from last race: Stalked wide; gave way. (4) Consistently runs wide at the first call (3 of last 5 starts). (5) No workout in last 30 days despite 19 days since last race. (6) Post 7 in a 8-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (7) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 32 (6/7) Mod2(W): 28 (6/7) Mod3(W): 20 (6/7) Mod1-LS: 30 (5/7) Mod2-LS: 36 (6/7) Mod3-LS: 88 (3/7) Mod4(Form): 31 (5/7) Win Prob: 30% Value Score: 3.58 ★ ML: 8.00 (7/1) Overlay %: 2.70 Fair Odds: 8.02 (7/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | F | D |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | F |
| Early Pace | D | D |
| Mid Pace | D | D |
| Late Pace | B | D |
| Finish Pos | B | D |
| Dirt Speed | C | D |
| Turf Speed | C | D |
| Distance Speed | C | C |
| Trainer Effectiveness | B | D |
| Jockey Effectiveness | B | D |
| 3rd Party Ratings | F | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | F |
| Early Pace | F | D |
| Mid Pace | F | D |
| Late Pace | B | C |
| Sprint FPS | B | D |
| Route FPS | B | D |
| Trainer Effectiveness | B | D |
| Jockey Effectiveness | B | D |
| 3rd Party Ratings | F | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | F |
| Early Pace | D | D |
| Mid Pace | D | D |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Early pace significantly above field median (E1: 82 vs field 78). (2) Strong speed 2 back (56), modest dip last out (50) — form reversal angle, ready to bounce back to top form. (3) Last race E1 pace (88.0) was 5.8 pts above personal avg (82.2) and horse still finished 4th — pace collapse victim; expect bounce if today's fractions are softer. (4) Career-best figure (70) buried in races 4–10 back — 18 pts above race median and 14 pts above recent form — market has forgotten the peak effort. (5) Had documented trouble last race (codes: ['D', 'F', 'L', 'T', 'V']) yet still finished 4th — a clean trip today sets up a form reversal.
⚠ Concerns:(1) 0 wins from 8 career starts on off tracks. (2) Poor record at this distance (0 wins from 10 recent starts). (3) Poor record at this track (0 wins from 25 starts). (4) Trip note from last race: Vied wide; flattened. (5) No workout in last 30 days despite 19 days since last race. (6) Post 8 in a 8-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (7) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 49 (5/7) Mod2(W): 33 (5/7) Mod3(W): 51 (5/7) Mod1-LS: 100 (1/7) Mod2-LS: 43 (5/7) Mod3-LS: 59 (5/7) Mod4(Form): 31 (6/7) Win Prob: 24.4% Value Score: 2.91 ★ ML: 8.00 (7/1) Overlay %: 5.15 Fair Odds: 6.39 (5/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | D |
| Early Pace | A | C |
| Mid Pace | A | C |
| Late Pace | C | D |
| Finish Pos | B | F |
| Dirt Speed | A | B |
| Turf Speed | C | D |
| Distance Speed | A | A |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | F | F |
| 3rd Party Ratings | B | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | F |
| Early Pace | A | B |
| Mid Pace | A | C |
| Late Pace | D | D |
| Sprint FPS | A | B |
| Route FPS | A | B |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | F | F |
| 3rd Party Ratings | B | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | F |
| Early Pace | B | C |
| Mid Pace | A | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 234-day layoff with a recent workout. (2) Hot trainer - high ITM rate (57%). (3) Hot jockey — high ITM rate (37%). (4) 4 workouts in last 30 days — horse appears sharp and fit. (5) Late pace significantly above field median (LP: 71 vs field 67). (6) Closer/presser in a race with pace pressure — ideal race setup for late runners. (7) Consistent workout spacing (8, 8 days) — disciplined training regimen. (8) Has won at today's distance (1320 yds) within the last 10 starts — proven ability at this trip. (9) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (10) Carries 5 lbs less than field median (117 lbs vs median 122 lbs). (11) Averages 65.3 speed pts in today's distance/surface configuration vs 57.0 in other configs (7 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Has not raced in 234 days. (2) 0 wins from 5 career starts on off tracks. (3) Trip note from last race: Wide; always outrun. (4) Speed figures are highly erratic over last 5 starts (σ = 9.6 pts: [54, 64, 77, 54, 58]) — unpredictable performer.
Mod1(W): 43 (4/6) Mod2(W): 44 (4/6) Mod3(W): 53 (4/6) Mod1-LS: 0 Mod2-LS: 43 (4/6) Mod3-LS: 0 Mod4(Form): 63 (3/6) Win Prob: 57.3% Value Score: 4.09 ★ ML: 4.50 (7/2) Overlay %: 0.08 Fair Odds: 6.09 (5/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | C | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | D |
| Early Pace | F | D |
| Mid Pace | F | D |
| Late Pace | B | C |
| Finish Pos | B | C |
| Dirt Speed | A | A |
| Turf Speed | B | C |
| Distance Speed | A | B |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | B | D |
| 3rd Party Ratings | C | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | D |
| Early Pace | F | D |
| Mid Pace | F | D |
| Late Pace | A | B |
| Sprint FPS | D | C |
| Route FPS | D | C |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | B | D |
| 3rd Party Ratings | C | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | D |
| Early Pace | F | C |
| Mid Pace | F | D |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Early pace significantly above field median (E1: 92 vs field 85). (2) Has won at today's distance (1320 yds) within the last 10 starts — proven ability at this trip. (3) Carries 7 lbs less than field median (115 lbs vs median 122 lbs). (4) Trainer 'GUERRERO MELECIO SALDANA' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (5) Career-best figure (75) buried in races 4–10 back — 12 pts above race median and 19 pts above recent form — market has forgotten the peak effort.
⚠ Concerns:(1) Repeatedly beaten at this class level (5 of last 5 starts). (2) Poor recent form - recent speed ratings well below career norm. (3) Consider there will be likely pace pressure in this race - multiple E types entered. (4) Poor record at this track (0 wins from 7 starts). (5) Tends to fade in the stretch at similar distances (9 of 10 starts). (6) Trip note from last race: Set pace; weakened. (7) Has not won in last 10 starts despite career wins.
Mod1(W): 49 (3/6) Mod2(W): 58 (3/6) Mod3(W): 59 (3/6) Mod1-LS: 13 (5/6) Mod2-LS: 50 (3/6) Mod3-LS: 72 (4/6) Mod4(Form): 47 (4/6) Win Prob: 31.4% Value Score: 2.85 ★ ML: 6.00 (5/1) Overlay %: 3.66 Fair Odds: 5.81 (5/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | D |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | D | D |
| Finish Pos | A | C |
| Dirt Speed | D | C |
| Turf Speed | C | C |
| Distance Speed | C | B |
| Trainer Effectiveness | C | D |
| Jockey Effectiveness | C | F |
| 3rd Party Ratings | B | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | F |
| Early Pace | A | A |
| Mid Pace | A | B |
| Late Pace | F | D |
| Sprint FPS | A | A |
| Route FPS | A | A |
| Trainer Effectiveness | C | D |
| Jockey Effectiveness | C | F |
| 3rd Party Ratings | B | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | D |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Dropping in class today ($12,500 → $7,500). (2) Speed average (75) well above field median (63). (3) Hot trainer - high ITM rate (36%). (4) Hot jockey — high ITM rate (43%). (5) Late pace significantly above field median (LP: 80 vs field 67). (6) Closer/presser in a race with pace pressure — ideal race setup for late runners. (7) Fourth race back from a 78-day layoff — often the peak fitness race. (8) Has won at today's distance (1320 yds) within the last 10 starts — proven ability at this trip. (9) Career-best figure (88) buried in races 4–10 back — 25 pts above race median and 21 pts above recent form — market has forgotten the peak effort. (10) Had documented trouble last race (codes: ['D', 'L', 'T']) yet still finished 4th — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Poor recent form - recent speed ratings well below career norm. (2) Trip note from last race: Trailed; lacked rally. (3) Has not won in last 10 starts despite career wins. (4) No workout in last 30 days despite 24 days since last race. (5) Dropping in class in consecutive starts ($62,500 → $16,000 → $12,500).
Mod1(W): 100 (1/6) Mod2(W): 100 (1/6) Mod3(W): 97 (2/6) Mod1-LS: 86 (2/6) Mod2-LS: 100 (1/6) Mod3-LS: 43 (5/6) Mod4(Form): 98 (2/6) Win Prob: 74.5% Value Score: 2.7 ★ ML: 1.80 (4/5) Overlay %: -10.47 Fair Odds: 4.86 (4/1) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | B |
| Early Pace | C | B |
| Mid Pace | A | B |
| Late Pace | A | B |
| Finish Pos | C | D |
| Dirt Speed | A | A |
| Turf Speed | A | B |
| Distance Speed | A | A |
| Trainer Effectiveness | A | D |
| Jockey Effectiveness | A | B |
| 3rd Party Ratings | A | B |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | D |
| Early Pace | C | C |
| Mid Pace | C | C |
| Late Pace | B | C |
| Sprint FPS | F | D |
| Route FPS | F | D |
| Trainer Effectiveness | A | D |
| Jockey Effectiveness | A | B |
| 3rd Party Ratings | A | B |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | D |
| Early Pace | C | B |
| Mid Pace | A | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Speed average (70) well above field median (63). (2) Hot jockey — high ITM rate (52%). (3) Late pace significantly above field median (LP: 74 vs field 67). (4) Strong speed 2 back (72), modest dip last out (64) — form reversal angle, ready to bounce back to top form. (5) Has won at today's distance (1320 yds) within the last 10 starts — proven ability at this trip. (6) Dropping in class ($7,500 vs last $20,000) after a 229-day freshening — trainer setup-for-win angle. (7) Returning from 229-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (8) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (9) Career-best figure (77) buried in races 4–10 back — 14 pts above race median and 5 pts above recent form — market has forgotten the peak effort. (10) Had documented trouble last race (codes: ['D', 'F', 'L', 'T']) yet still finished 4th — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 229 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Trip note from last race: Rail trip; flattened. (4) No workout in last 30 days despite 229 days since last race.
Mod1(W): 88 (2/6) Mod2(W): 92 (2/6) Mod3(W): 100 (1/6) Mod1-LS: 100 (1/6) Mod2-LS: 86 (2/6) Mod3-LS: 99 (2/6) Mod4(Form): 100 (1/6) Win Prob: 73.2% Value Score: 2.47 ★ ML: 1.60 (3/5) Overlay %: -13.24 Fair Odds: 5.09 (4/1) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | C |
| Early Pace | B | B |
| Mid Pace | B | B |
| Late Pace | A | C |
| Finish Pos | A | B |
| Dirt Speed | C | B |
| Turf Speed | A | C |
| Distance Speed | C | C |
| Trainer Effectiveness | C | D |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | C |
| Early Pace | C | C |
| Mid Pace | A | B |
| Late Pace | A | C |
| Sprint FPS | B | B |
| Route FPS | A | B |
| Trainer Effectiveness | C | D |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | C |
| Early Pace | B | B |
| Mid Pace | B | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Closer/presser in a race with pace pressure — ideal race setup for late runners. (2) Has won at today's distance (1320 yds) within the last 10 starts — proven ability at this trip. (3) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo.
⚠ Concerns:(1) 0 wins from 7 career starts on off tracks. (2) Trip note from last race: Chased 3w; weakened.
Mod1(W): 21 (5/6) Mod2(W): 24 (5/6) Mod3(W): 31 (5/6) Mod1-LS: 73 (3/6) Mod2-LS: 22 (5/6) Mod3-LS: 100 (1/6) Mod4(Form): 24 (5/6) Win Prob: 31.9% Value Score: 4.54 ★ ML: 10.00 (9/1) Overlay %: 6.26 Fair Odds: 6.54 (6/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | D |
| Early Pace | C | B |
| Mid Pace | C | C |
| Late Pace | F | D |
| Finish Pos | D | D |
| Dirt Speed | C | B |
| Turf Speed | D | D |
| Distance Speed | D | C |
| Trainer Effectiveness | B | D |
| Jockey Effectiveness | C | D |
| 3rd Party Ratings | C | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | D |
| Early Pace | B | B |
| Mid Pace | C | B |
| Late Pace | C | D |
| Sprint FPS | C | C |
| Route FPS | C | C |
| Trainer Effectiveness | B | D |
| Jockey Effectiveness | C | D |
| 3rd Party Ratings | C | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | D |
| Early Pace | C | B |
| Mid Pace | C | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 31-day layoff with a recent workout. (2) Has won at today's distance (1320 yds) within the last 10 starts — proven ability at this trip. (3) Returning from 31-day layoff with a bullet workout — trainer signaling extra readiness for today's spot.
⚠ Concerns:(1) Has not raced in 31 days. (2) Rising in class today ($5,000 → $7,500). (3) Consider there will be likely pace pressure in this race - multiple E types entered. (4) Trip note from last race: Chsd btwn; retreated. (5) Rising in class ($5,000 → $7,500) after finishing 5 last out — double negative. (6) First start at PRX — never raced here before (last seen at: PEN, CT).
Mod1(W): 14 (6/6) Mod2(W): 9 (6/6) Mod3(W): 19 (6/6) Mod1-LS: 9 (6/6) Mod2-LS: 7 (6/6) Mod3-LS: 31 (6/6) Mod4(Form): 14 (6/6) Win Prob: 24.2% Value Score: 4.07 ★ ML: 12.00 (10/1) Overlay %: 5.24 Fair Odds: 7.95 (7/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | F | F |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | D |
| Early Pace | A | B |
| Mid Pace | C | C |
| Late Pace | C | D |
| Finish Pos | B | C |
| Dirt Speed | F | C |
| Turf Speed | C | C |
| Distance Speed | F | D |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | F | F |
| 3rd Party Ratings | F | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | F |
| Early Pace | D | C |
| Mid Pace | D | C |
| Late Pace | C | D |
| Sprint FPS | A | A |
| Route FPS | B | B |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | F | F |
| 3rd Party Ratings | F | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | D |
| Early Pace | A | B |
| Mid Pace | C | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Last race E1 pace (89.0) was 6.3 pts above personal avg (82.7) and horse still finished 8th — pace collapse victim; expect bounce if today's fractions are softer.
⚠ Concerns:(1) Repeatedly beaten at this class level (5 of last 5 starts). (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Speed average (56) well below field median (63). (4) 0 wins from 12 career starts on off tracks. (5) Poor record at this distance (0 wins from 10 recent starts). (6) Trip note from last race: Chased turn; faded. (7) Consistently breaks behind post position (3 of last 5 starts). (8) No workout in last 30 days despite 19 days since last race. (9) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 0 Mod2(W): 0 Mod3(W): 0 Mod1-LS: 22 (4/6) Mod2-LS: 0 Mod3-LS: 83 (3/6) Mod4(Form): 0 Win Prob: 17% Value Score: 3.53 ★ ML: 15.00 (15/1) Overlay %: 8.48 Fair Odds: 6.52 (6/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | C | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | F | F |
| Early Pace | D | C |
| Mid Pace | D | C |
| Late Pace | C | D |
| Finish Pos | F | F |
| Dirt Speed | B | B |
| Turf Speed | D | D |
| Distance Speed | B | B |
| Trainer Effectiveness | D | F |
| Jockey Effectiveness | D | F |
| 3rd Party Ratings | D | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | D |
| Early Pace | A | B |
| Mid Pace | B | B |
| Late Pace | D | D |
| Sprint FPS | C | B |
| Route FPS | C | C |
| Trainer Effectiveness | D | F |
| Jockey Effectiveness | D | F |
| 3rd Party Ratings | D | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | F |
| Early Pace | D | C |
| Mid Pace | D | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Hot trainer - high ITM rate (57%). (2) Hot jockey — high ITM rate (46%). (3) Track specialist — 2 wins from 7 starts here (29%). (4) Early pace significantly above field median (E1: 88 vs field 79). (5) Fourth race back from a 133-day layoff — often the peak fitness race. (6) Has won at today's distance (1540 yds) within the last 10 starts — proven ability at this trip. (7) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (8) Had documented trouble last race (codes: ['B', 'D', 'F', 'L', 'S', 'T']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Trip note from last race: Stalk3w;bid4w;flattend. (2) No workout in last 30 days despite 24 days since last race.
Mod1(W): 100 (1/6) Mod2(W): 100 (1/6) Mod3(W): 100 (1/6) Mod1-LS: 100 (1/6) Mod2-LS: 100 (1/6) Mod3-LS: 73 (4/6) Mod4(Form): 100 (1/6) Win Prob: 48.8% Value Score: 2.19 ★ ML: 2.50 (3/2) Overlay %: -4.62 Fair Odds: 4.67 (7/2) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | C |
| Early Pace | A | A |
| Mid Pace | A | B |
| Late Pace | B | C |
| Finish Pos | B | B |
| Dirt Speed | B | B |
| Turf Speed | C | D |
| Distance Speed | A | B |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | B | B |
| 3rd Party Ratings | A | B |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | C |
| Early Pace | A | B |
| Mid Pace | A | B |
| Late Pace | B | C |
| Sprint FPS | A | A |
| Route FPS | A | B |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | B | B |
| 3rd Party Ratings | A | B |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | C |
| Early Pace | A | B |
| Mid Pace | A | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) In the money in last 3 consecutive starts. (2) Early pace significantly above field median (E1: 85 vs field 79). (3) Has won at today's distance (1540 yds) within the last 10 starts — proven ability at this trip. (4) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (5) Trainer 'GONZALEZ-MILIAN JOSE G' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (6) Had documented trouble last race (codes: ['D', 'L', 'T']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Speed average (60) well below field median (66). (2) Trip note from last race: Pace; weakened late. (3) No workout in last 30 days despite 25 days since last race.
Mod1(W): 27 (6/6) Mod2(W): 35 (6/6) Mod3(W): 38 (5/6) Mod1-LS: 6 (6/6) Mod2-LS: 29 (6/6) Mod3-LS: 68 (5/6) Mod4(Form): 36 (6/6) Win Prob: 46.7% Value Score: 4.2 ★ ML: 6.00 (5/1) Overlay %: 2.21 Fair Odds: 6.50 (5/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | D |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | D |
| Early Pace | A | B |
| Mid Pace | B | C |
| Late Pace | F | D |
| Finish Pos | C | C |
| Dirt Speed | D | C |
| Turf Speed | C | D |
| Distance Speed | D | C |
| Trainer Effectiveness | C | D |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | B | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | D |
| Early Pace | A | A |
| Mid Pace | A | B |
| Late Pace | F | D |
| Sprint FPS | B | B |
| Route FPS | A | B |
| Trainer Effectiveness | C | D |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | B | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | F |
| Early Pace | A | B |
| Mid Pace | B | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) In the money in last 3 consecutive starts. (2) Career-best figure (79) buried in races 4–10 back — 13 pts above race median and 11 pts above recent form — market has forgotten the peak effort. (3) Had documented trouble last race (codes: ['D', 'L', 'O', 'S', 'T', 'U']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Poor record at this distance (0 wins from 6 recent starts). (2) Trip note from last race: Rallied outside;gamely. (3) Consistently breaks behind post position (3 of last 5 starts). (4) Has not won in last 10 starts despite career wins. (5) No workout in last 30 days despite 25 days since last race. (6) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 61 (3/6) Mod2(W): 59 (3/6) Mod3(W): 48 (2/6) Mod1-LS: 25 (4/6) Mod2-LS: 57 (4/6) Mod3-LS: 65 (6/6) Mod4(Form): 59 (3/6) Win Prob: 43% Value Score: 3.04 ★ ML: 4.50 (7/2) Overlay %: 0.24 Fair Odds: 5.95 (5/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | C | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | C |
| Early Pace | F | D |
| Mid Pace | F | D |
| Late Pace | A | B |
| Finish Pos | A | B |
| Dirt Speed | A | B |
| Turf Speed | A | C |
| Distance Speed | A | B |
| Trainer Effectiveness | C | D |
| Jockey Effectiveness | C | C |
| 3rd Party Ratings | A | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | D |
| Early Pace | F | D |
| Mid Pace | F | D |
| Late Pace | C | C |
| Sprint FPS | F | D |
| Route FPS | F | D |
| Trainer Effectiveness | C | D |
| Jockey Effectiveness | C | C |
| 3rd Party Ratings | A | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | D |
| Early Pace | F | D |
| Mid Pace | F | D |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Hot trainer - high ITM rate (50%). (2) Has won at today's distance (1540 yds) within the last 10 starts — proven ability at this trip. (3) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (4) Speed improved +8 pts then +7 pts in last 2 starts (60 → 68 → 75) — trainer is progressively building fitness. (5) Trainer 'GUERRERO J GUADALUPE' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (6) Had documented trouble last race (codes: ['B', 'D', 'F', 'L', 'O', 'S', 'T', 'U']) yet still finished 1st — a clean trip today sets up a form reversal. (7) Averages 66.3 speed pts in today's distance/surface configuration vs 52.0 in other configs (6 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Rising in class today ($7,500 → $12,500). (2) Was claimed from its most recent race - new connections. (3) Speed average (61) well below field median (66). (4) 0 wins from 5 career starts on off tracks. (5) Trip note from last race: Blockd turn;split foes. (6) 0 wins from post 4 in 4 recent starts. (7) Last race was career-best speed (75) — bounce risk after peak effort. (8) Speed figures are highly erratic over last 5 starts (σ = 10.5 pts: [75, 68, 60, 74, 50]) — unpredictable performer. (9) Two consecutive 5+ pt speed jumps (60 → 68 → 75) and last race speed is well above career average (61) — high bounce risk after back-to-back peak efforts.
Mod1(W): 50 (5/6) Mod2(W): 65 (2/6) Mod3(W): 30 (6/6) Mod1-LS: 19 (5/6) Mod2-LS: 59 (3/6) Mod3-LS: 80 (3/6) Mod4(Form): 49 (4/6) Win Prob: 49.9% Value Score: 3.85 ★ ML: 5.00 (4/1) Overlay %: 1.23 Fair Odds: 6.04 (5/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | D |
| Early Pace | D | D |
| Mid Pace | D | D |
| Late Pace | D | D |
| Finish Pos | D | D |
| Dirt Speed | C | C |
| Turf Speed | A | B |
| Distance Speed | F | C |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | C | B |
| 3rd Party Ratings | C | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | C |
| Early Pace | C | D |
| Mid Pace | C | C |
| Late Pace | A | B |
| Sprint FPS | C | C |
| Route FPS | C | B |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | C | B |
| 3rd Party Ratings | C | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | D |
| Early Pace | D | D |
| Mid Pace | D | D |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 46-day layoff with a recent workout. (2) Hot trainer - high ITM rate (43%). (3) Hot jockey — high ITM rate (52%). (4) Early pace significantly above field median (E1: 83 vs field 79). (5) Has won at today's distance (1540 yds) within the last 10 starts — proven ability at this trip. (6) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (7) Had documented trouble last race (codes: ['B', 'D', 'F', 'L']) yet still finished 4th — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 46 days. (2) 0 wins from 5 career starts on off tracks. (3) Trip note from last race: Far back; mild bid.
Mod1(W): 56 (4/6) Mod2(W): 54 (5/6) Mod3(W): 48 (3/6) Mod1-LS: 0 Mod2-LS: 54 (5/6) Mod3-LS: 100 (1/6) Mod4(Form): 48 (5/6) Win Prob: 52.6% Value Score: 4.05 ★ ML: 5.00 (4/1) Overlay %: 1.28 Fair Odds: 6.01 (5/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | C | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | C |
| Early Pace | B | C |
| Mid Pace | A | C |
| Late Pace | B | C |
| Finish Pos | B | B |
| Dirt Speed | A | B |
| Turf Speed | C | D |
| Distance Speed | B | C |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | C | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | C |
| Early Pace | D | D |
| Mid Pace | D | D |
| Late Pace | A | B |
| Sprint FPS | D | D |
| Route FPS | D | D |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | C | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | C |
| Early Pace | B | C |
| Mid Pace | A | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Career-best speed figure (67) recorded in last 1-2 starts — peaking form. (2) Has won at today's distance (1540 yds) within the last 10 starts — proven ability at this trip. (3) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (4) Had documented trouble last race (codes: ['D', 'L', 'S', 'T', 'U']) yet still finished 4th — a clean trip today sets up a form reversal. (5) Averages 59.8 speed pts in today's distance/surface configuration vs 51.0 in other configs (8 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Speed average (58) well below field median (66). (2) Trip note from last race: Chased turn; mildly. (3) No workout in last 30 days despite 25 days since last race.
Mod1(W): 0 Mod2(W): 0 Mod3(W): 0 Mod1-LS: 58 (2/6) Mod2-LS: 0 Mod3-LS: 95 (2/6) Mod4(Form): 0 Win Prob: 37.8% Value Score: 5.34 ★ ML: 10.00 (9/1) Overlay %: 4.62 Fair Odds: 7.55 (7/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | F | D |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | F | D |
| Early Pace | C | D |
| Mid Pace | C | D |
| Late Pace | C | C |
| Finish Pos | F | F |
| Dirt Speed | D | C |
| Turf Speed | C | D |
| Distance Speed | C | C |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | F | F |
| 3rd Party Ratings | F | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | C |
| Early Pace | B | B |
| Mid Pace | B | B |
| Late Pace | D | C |
| Sprint FPS | A | B |
| Route FPS | B | B |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | F | F |
| 3rd Party Ratings | F | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | D |
| Early Pace | C | C |
| Mid Pace | C | D |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 243-day layoff with a recent workout. (2) Hot jockey — high ITM rate (46%). (3) 3 workouts in last 30 days — horse appears sharp and fit. (4) Track specialist — 2 wins from 8 starts here (25%). (5) Consistent workout spacing (7, 7 days) — disciplined training regimen. (6) Has won at today's distance (1540 yds) within the last 10 starts — proven ability at this trip. (7) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (8) Had documented trouble last race (codes: ['D', 'L', 'S']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 243 days. (2) Trip note from last race: Wide; rallied; missed.
Mod1(W): 61 (2/6) Mod2(W): 57 (4/6) Mod3(W): 45 (4/6) Mod1-LS: 30 (3/6) Mod2-LS: 65 (2/6) Mod3-LS: 0 Mod4(Form): 88 (2/6) Win Prob: 68.9% Value Score: 3.54 ★ ML: 3.00 (2/1) Overlay %: -4.97 Fair Odds: 5.90 (5/1) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | C |
| Early Pace | C | D |
| Mid Pace | C | D |
| Late Pace | C | C |
| Finish Pos | C | B |
| Dirt Speed | B | B |
| Turf Speed | C | D |
| Distance Speed | C | C |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | A | B |
| 3rd Party Ratings | D | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | C |
| Early Pace | C | D |
| Mid Pace | C | C |
| Late Pace | C | C |
| Sprint FPS | C | C |
| Route FPS | C | B |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | A | B |
| 3rd Party Ratings | D | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | C |
| Early Pace | C | D |
| Mid Pace | C | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 39-day layoff with a recent workout. (2) Significantly better on off tracks (off: 38 vs fast: 5). (3) Career-best speed figure (5) recorded in last 1-2 starts — peaking form. (4) Closer/presser in a race with pace pressure — ideal race setup for late runners. (5) Returning from 39-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (6) Cutting back to sprint (1320 yds) from routes — sprint speed figures (41.0) are 9.6 pts better than route figures (31.4).
⚠ Concerns:(1) Has not raced in 39 days. (2) Speed average (22) well below field median (57). (3) Limited experience at today's distance (1 start). (4) Moving from a route to a sprint today. (5) Unproven on dirt surface (2 starts). (6) Trip note from last race: Steadied 1st; gave way. (7) Was the betting favorite in the last race but finished off the board.
Mod1(W): 4 (7/7) Mod2(W): 9 (7/7) Mod3(W): 0 (7/7) Mod1-LS: 11 (7/7) Mod2-LS: 7 (7/7) Mod3-LS: 0 Mod4(Form): 17 (7/7) Win Prob: 23.5% Value Score: 3.98 ★ ML: 12.00 (10/1) Overlay %: 1.72 Fair Odds: 12.13 (12/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | F | F |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | F | F |
| Early Pace | B | C |
| Mid Pace | F | D |
| Late Pace | F | F |
| Finish Pos | D | F |
| Dirt Speed | F | D |
| Turf Speed | C | D |
| Distance Speed | C | D |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | F | F |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | F |
| Early Pace | B | C |
| Mid Pace | F | D |
| Late Pace | F | F |
| Sprint FPS | B | D |
| Route FPS | D | D |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | F | F |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | F |
| Early Pace | F | D |
| Mid Pace | F | D |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Dropping in class today ($28,000 → $15,000). (2) Hot trainer - high ITM rate (48%). (3) Big last-race effort (63) — 10 pts above recent average. (4) Early pace significantly above field median (E1: 84 vs field 80). (5) Closer/presser in a race with pace pressure — ideal race setup for late runners. (6) Switching turf-to-dirt with a strong turf pedigree rating (101) — pedigree suggests main-track improvement is likely. (7) Last race E1 pace (94.0) was 9.5 pts above personal avg (84.5) and horse still finished 9th — pace collapse victim; expect bounce if today's fractions are softer. (8) Averages 59.7 speed pts in today's distance/surface configuration vs 52.3 in other configs (3 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Consider there will be likely pace pressure in this race - multiple E types entered. (2) Moving from a route to a sprint today. (3) Switching from turf to dirt today. (4) Trip note from last race: Duel; weakened. (5) Dropping in class in consecutive starts ($50,000 → $30,000 → $28,000). (6) Speed figures are highly erratic over last 5 starts (σ = 10.4 pts: [63, 52, 65, 42, 66]) — unpredictable performer. (7) 0 wins from 5 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 65 (5/7) Mod2(W): 66 (5/7) Mod3(W): 64 (5/7) Mod1-LS: 40 (5/7) Mod2-LS: 61 (5/7) Mod3-LS: 100 (1/7) Mod4(Form): 53 (4/7) Win Prob: 36.3% Value Score: 3.31 ★ ML: 6.00 (5/1) Overlay %: 3.07 Fair Odds: 6.13 (5/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | D |
| Early Pace | A | B |
| Mid Pace | A | C |
| Late Pace | D | D |
| Finish Pos | C | F |
| Dirt Speed | C | C |
| Turf Speed | A | C |
| Distance Speed | A | C |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | B | D |
| 3rd Party Ratings | C | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | D |
| Early Pace | A | A |
| Mid Pace | A | B |
| Late Pace | D | D |
| Sprint FPS | A | B |
| Route FPS | A | B |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | B | D |
| 3rd Party Ratings | C | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | F |
| Early Pace | A | B |
| Mid Pace | B | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Big last-race effort (40) — 8 pts above recent average. (2) Closer/presser in a race with pace pressure — ideal race setup for late runners. (3) Fourth race back from a 104-day layoff — often the peak fitness race. (4) Carries 9 lbs less than field median (113 lbs vs median 122 lbs).
⚠ Concerns:(1) Speed average (34) well below field median (57). (2) Trip note from last race: Far back throughout. (3) Last race was career-best speed (40) — bounce risk after peak effort.
Mod1(W): 0 Mod2(W): 0 Mod3(W): 0 Mod1-LS: 0 Mod2-LS: 0 Mod3-LS: 26 (7/7) Mod4(Form): 0 Win Prob: 17.6% Value Score: 3.67 ★ ML: 15.00 (15/1) Overlay %: 4.94 Fair Odds: 9.28 (8/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | D |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | F |
| Early Pace | F | D |
| Mid Pace | D | D |
| Late Pace | D | F |
| Finish Pos | D | F |
| Dirt Speed | D | D |
| Turf Speed | C | D |
| Distance Speed | D | D |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | C | D |
| 3rd Party Ratings | D | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | F |
| Early Pace | F | D |
| Mid Pace | D | D |
| Late Pace | D | F |
| Sprint FPS | F | D |
| Route FPS | F | D |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | C | D |
| 3rd Party Ratings | D | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | F |
| Early Pace | A | B |
| Mid Pace | C | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 51-day layoff with a recent workout. (2) Speed average (64) well above field median (57). (3) Hot trainer - high ITM rate (59%). (4) Strong trainer/jockey combo - 28 wins from 67 starts (42%). (5) Hot jockey — high ITM rate (52%). (6) Early pace significantly above field median (E1: 84 vs field 80). (7) Late pace significantly above field median (LP: 70 vs field 64). (8) Speed improved +4 pts then +4 pts in last 2 starts (60 → 64 → 68) — trainer is progressively building fitness. (9) Trainer 'PINO MICHAEL V' has 4 horses in today's card all showing last-race improvement — barn appears sharp right now. (10) Had documented trouble last race (codes: ['D', 'S', 'T']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 51 days. (2) Was claimed from its most recent race - new connections. (3) Consider there will be likely pace pressure in this race - multiple E types entered. (4) Poor record at this distance (0 wins from 6 recent starts). (5) Poor record at this track (0 wins from 8 starts). (6) Tends to fade in the stretch at similar distances (4 of 6 starts). (7) Trip note from last race: Wdnd; resisted; tired. (8) 0 wins from 8 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 100 (1/7) Mod2(W): 100 (1/7) Mod3(W): 100 (2/7) Mod1-LS: 100 (1/7) Mod2-LS: 100 (1/7) Mod3-LS: 87 (2/7) Mod4(Form): 93 (2/7) Win Prob: 47.3% Value Score: 2.47 ★ ML: 3.00 (2/1) Overlay %: -4.02 Fair Odds: 5.60 (9/2) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | D |
| Early Pace | A | C |
| Mid Pace | A | C |
| Late Pace | B | C |
| Finish Pos | B | D |
| Dirt Speed | A | C |
| Turf Speed | C | D |
| Distance Speed | B | C |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | D |
| Early Pace | A | B |
| Mid Pace | A | B |
| Late Pace | B | C |
| Sprint FPS | B | C |
| Route FPS | B | B |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | D |
| Early Pace | B | B |
| Mid Pace | B | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Hot trainer - high ITM rate (48%). (2) Career-best speed figure (58) recorded in last 1-2 starts — peaking form. (3) Hot jockey — high ITM rate (41%). (4) Closer/presser in a race with pace pressure — ideal race setup for late runners.
⚠ Concerns:(1) Has not raced in 48 days. (2) First time at today's distance. (3) Moving from a route to a sprint today. (4) Today's distance is shorter than any previous start. (5) Unproven on dirt surface (1 start). (6) Trip note from last race: Bmp brk;3p;no kick.
Mod1(W): 53 (6/7) Mod2(W): 53 (6/7) Mod3(W): 51 (6/7) Mod1-LS: 30 (6/7) Mod2-LS: 55 (6/7) Mod3-LS: 66 (5/7) Mod4(Form): 51 (5/7) Win Prob: 42.1% Value Score: 3.85 ★ ML: 6.00 (5/1) Overlay %: 1.32 Fair Odds: 7.14 (6/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | D |
| Early Pace | D | D |
| Mid Pace | D | D |
| Late Pace | B | D |
| Finish Pos | F | F |
| Dirt Speed | D | D |
| Turf Speed | A | C |
| Distance Speed | F | F |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | B | C |
| 3rd Party Ratings | D | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | D |
| Early Pace | D | D |
| Mid Pace | D | D |
| Late Pace | B | D |
| Sprint FPS | D | D |
| Route FPS | D | D |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | B | C |
| 3rd Party Ratings | D | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | A |
| Early Pace | D | D |
| Mid Pace | D | D |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 33-day layoff with a recent workout. (2) Dropping in class today ($25,000 → $15,000). (3) Speed average (62) well above field median (57). (4) Career-best speed figure (73) recorded in last 1-2 starts — peaking form. (5) Late pace significantly above field median (LP: 75 vs field 64). (6) Closer/presser in a race with pace pressure — ideal race setup for late runners. (7) Dropping in class ($15,000 vs last $25,000) after a 33-day freshening — trainer setup-for-win angle.
⚠ Concerns:(1) Has not raced in 33 days. (2) Poor record at this distance (0 wins from 9 recent starts). (3) Poor record at this track (0 wins from 9 starts). (4) Trip note from last race: Passed tired rivals. (5) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 90 (3/7) Mod2(W): 93 (2/7) Mod3(W): 91 (3/7) Mod1-LS: 74 (3/7) Mod2-LS: 93 (2/7) Mod3-LS: 75 (3/7) Mod4(Form): 100 (1/7) Win Prob: 58.2% Value Score: 2.66 ★ ML: 2.50 (3/2) Overlay %: -7.87 Fair Odds: 6.12 (5/1) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | D |
| Early Pace | C | D |
| Mid Pace | B | C |
| Late Pace | A | B |
| Finish Pos | A | B |
| Dirt Speed | A | C |
| Turf Speed | C | D |
| Distance Speed | A | C |
| Trainer Effectiveness | D | C |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | B | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | C |
| Early Pace | D | D |
| Mid Pace | B | C |
| Late Pace | A | B |
| Sprint FPS | D | D |
| Route FPS | B | C |
| Trainer Effectiveness | D | C |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | B | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | D |
| Early Pace | D | C |
| Mid Pace | A | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Big last-race effort (69) — 14 pts above recent average. (2) Hot jockey — high ITM rate (43%). (3) Speed improved +16 pts then +8 pts in last 2 starts (45 → 61 → 69) — trainer is progressively building fitness. (4) Had documented trouble last race (codes: ['D', 'F', 'S', 'T', 'U']) yet still finished 4th — a clean trip today sets up a form reversal. (5) Averages 57.2 speed pts in today's distance/surface configuration vs 51.0 in other configs (4 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Repeatedly beaten at this class level (3 of last 5 starts). (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Poor record at this distance (0 wins from 4 recent starts). (4) Poor record at this track (0 wins from 6 starts). (5) Trip note from last race: Std far turn; std 1/8. (6) Last race was career-best speed (69) — bounce risk after peak effort. (7) No workout in last 30 days despite 18 days since last race. (8) Post 7 in a 8-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (9) Speed figures are highly erratic over last 5 starts (σ = 10.7 pts: [69, 61, 45, 58, 44]) — unpredictable performer. (10) 0 wins from 6 starts on dirt in last 10 — repeated failure on today's surface. (11) Two consecutive 5+ pt speed jumps (45 → 61 → 69) and last race speed is well above career average (55) — high bounce risk after back-to-back peak efforts.
Mod1(W): 72 (4/7) Mod2(W): 71 (4/7) Mod3(W): 72 (4/7) Mod1-LS: 54 (4/7) Mod2-LS: 65 (4/7) Mod3-LS: 75 (4/7) Mod4(Form): 50 (6/7) Win Prob: 40.8% Value Score: 3.72 ★ ML: 6.00 (5/1) Overlay %: 2.11 Fair Odds: 6.65 (6/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | C | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | F |
| Early Pace | B | C |
| Mid Pace | B | D |
| Late Pace | C | D |
| Finish Pos | B | F |
| Dirt Speed | B | C |
| Turf Speed | C | D |
| Distance Speed | B | C |
| Trainer Effectiveness | C | B |
| Jockey Effectiveness | A | B |
| 3rd Party Ratings | B | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | D |
| Early Pace | B | B |
| Mid Pace | B | C |
| Late Pace | C | D |
| Sprint FPS | A | B |
| Route FPS | A | B |
| Trainer Effectiveness | C | B |
| Jockey Effectiveness | A | B |
| 3rd Party Ratings | B | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | F |
| Early Pace | C | C |
| Mid Pace | A | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Speed average (62) well above field median (57). (2) Hot trainer - high ITM rate (59%). (3) Career-best speed figure (69) recorded in last 1-2 starts — peaking form. (4) Big last-race effort (68) — 8 pts above recent average. (5) Late pace significantly above field median (LP: 77 vs field 64). (6) Carries 7 lbs less than field median (115 lbs vs median 122 lbs). (7) Trainer 'PINO MICHAEL V' has 4 horses in today's card all showing last-race improvement — barn appears sharp right now. (8) Had documented trouble last race (codes: ['L', 'O', 'S', 'T', 'V']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Rising in class today ($10,000 → $15,000). (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Trip note from last race: Very slow start; rail. (4) Consistently breaks behind post position (3 of last 5 starts). (5) Post 8 in a 8-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path.
Mod1(W): 100 (2/7) Mod2(W): 87 (3/7) Mod3(W): 100 (1/7) Mod1-LS: 81 (2/7) Mod2-LS: 89 (3/7) Mod3-LS: 50 (6/7) Mod4(Form): 76 (3/7) Win Prob: 54.7% Value Score: 3.56 ★ ML: 4.00 (3/1) Overlay %: -1.28 Fair Odds: 6.11 (5/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | D |
| Early Pace | D | D |
| Mid Pace | C | D |
| Late Pace | A | B |
| Finish Pos | A | D |
| Dirt Speed | B | C |
| Turf Speed | C | D |
| Distance Speed | F | F |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | F | F |
| 3rd Party Ratings | A | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | D |
| Early Pace | C | D |
| Mid Pace | C | D |
| Late Pace | A | B |
| Sprint FPS | C | D |
| Route FPS | C | D |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | F | F |
| 3rd Party Ratings | A | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | D |
| Early Pace | B | C |
| Mid Pace | D | D |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 282-day layoff with a recent workout. (2) Has a bullet work (fastest at track that day) — sharp conditioning signal. (3) Late pace significantly above field median (LP: 82 vs field 77). (4) Closer/presser in a race with pace pressure — ideal race setup for late runners. (5) Switching turf-to-dirt with a strong turf pedigree rating (98) — pedigree suggests main-track improvement is likely. (6) Returning from 282-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (7) Career-best figure (85) buried in races 4–10 back — 15 pts above race median and 9 pts above recent form — market has forgotten the peak effort. (8) Averages 77.8 speed pts in today's distance/surface configuration vs 32.0 in other configs (8 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Has not raced in 282 days. (2) Switching from turf to dirt today. (3) Poor record at this distance (0 wins from 8 recent starts). (4) Trip note from last race: Never involved. (5) Speed figures are highly erratic over last 5 starts (σ = 30.5 pts: [9, 76, 70, 77, 83]) — unpredictable performer. (6) 0 wins from 8 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 0 Mod2(W): 0 Mod3(W): 0 Mod1-LS: 36 (4/7) Mod2-LS: 0 Mod3-LS: 0 Mod4(Form): 0 Win Prob: 28.6% Value Score: 4.85 ★ ML: 12.00 (10/1) Overlay %: 2.38 Fair Odds: 11.09 (10/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | F | F |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | C |
| Early Pace | D | D |
| Mid Pace | F | D |
| Late Pace | A | A |
| Finish Pos | D | D |
| Dirt Speed | A | A |
| Turf Speed | B | C |
| Distance Speed | A | A |
| Trainer Effectiveness | F | D |
| Jockey Effectiveness | F | D |
| 3rd Party Ratings | F | F |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | F |
| Early Pace | F | D |
| Mid Pace | D | D |
| Late Pace | A | A |
| Sprint FPS | A | A |
| Route FPS | B | A |
| Trainer Effectiveness | F | D |
| Jockey Effectiveness | F | D |
| 3rd Party Ratings | F | F |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | C |
| Early Pace | C | D |
| Mid Pace | B | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Significantly better on off tracks (off: 78 vs fast: 72). (2) Hot trainer - high ITM rate (60%). (3) Strong trainer/jockey combo - 13 wins from 42 starts (31%). (4) Hot jockey — high ITM rate (52%). (5) Fourth race back from a 83-day layoff — often the peak fitness race. (6) Trainer 'NESS JAMIE' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (7) Career-best figure (78) buried in races 4–10 back — 8 pts above race median and 7 pts above recent form — market has forgotten the peak effort. (8) Had documented trouble last race (codes: ['B', 'L', 'T', 'U']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Rising in class today ($20,000 → $40,000). (2) Was claimed from its most recent race - new connections. (3) Consider there will be likely pace pressure in this race - multiple E types entered. (4) Moving from a sprint to a route today. (5) Poor record at this distance (0 wins from 7 recent starts). (6) Trip note from last race: 3-4p;btw;6p upr;rally. (7) No workout in last 30 days despite 21 days since last race. (8) Stepping up to $40,000 — highest class level in last 10 starts (previous high: $20,000). (9) 0 wins from 6 starts on dirt in last 10 — repeated failure on today's surface. (10) First start at PRX — never raced here before (last seen at: KEE, CNL, TP).
Mod1(W): 54 (4/7) Mod2(W): 74 (3/7) Mod3(W): 90 (2/7) Mod1-LS: 8 (7/7) Mod2-LS: 65 (4/7) Mod3-LS: 47 (3/7) Mod4(Form): 62 (4/7) Win Prob: 40.2% Value Score: 3.14 ★ ML: 5.00 (4/1) Overlay %: 1.70 Fair Odds: 5.91 (5/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | C |
| Early Pace | D | C |
| Mid Pace | D | D |
| Late Pace | D | B |
| Finish Pos | F | F |
| Dirt Speed | B | C |
| Turf Speed | A | B |
| Distance Speed | B | C |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | B |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | C |
| Early Pace | D | D |
| Mid Pace | F | D |
| Late Pace | B | B |
| Sprint FPS | D | C |
| Route FPS | D | D |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | B |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | C |
| Early Pace | B | C |
| Mid Pace | D | D |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Strong trainer/jockey combo - 8 wins from 27 starts (30%). (2) Career-best speed figure (71) recorded in last 1-2 starts — peaking form. (3) Closer/presser in a race with pace pressure — ideal race setup for late runners. (4) Had documented trouble last race (codes: ['L']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Moving from a sprint to a route today. (2) Poor record at this track (0 wins from 6 starts). (3) Trip note from last race: Rail rally; gamely. (4) 0 wins from 6 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 64 (3/7) Mod2(W): 73 (4/7) Mod3(W): 68 (4/7) Mod1-LS: 0 Mod2-LS: 74 (3/7) Mod3-LS: 21 (7/7) Mod4(Form): 80 (3/7) Win Prob: 55.7% Value Score: 3.64 ★ ML: 4.00 (3/1) Overlay %: -2.10 Fair Odds: 6.56 (6/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | C |
| Early Pace | A | C |
| Mid Pace | B | C |
| Late Pace | C | B |
| Finish Pos | D | B |
| Dirt Speed | D | C |
| Turf Speed | D | D |
| Distance Speed | D | F |
| Trainer Effectiveness | D | B |
| Jockey Effectiveness | B | B |
| 3rd Party Ratings | B | B |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | C |
| Early Pace | C | C |
| Mid Pace | B | C |
| Late Pace | D | B |
| Sprint FPS | C | C |
| Route FPS | C | C |
| Trainer Effectiveness | D | B |
| Jockey Effectiveness | B | B |
| 3rd Party Ratings | B | B |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | C |
| Early Pace | A | B |
| Mid Pace | A | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 114-day layoff with a recent workout. (2) Career-best speed figure (71) recorded in last 1-2 starts — peaking form. (3) Returning from 114-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (4) Had documented trouble last race (codes: ['D', 'F', 'O', 'V']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 114 days. (2) Rising in class today ($30,000 → $40,000). (3) Consider there will be likely pace pressure in this race - multiple E types entered. (4) Limited experience at today's distance (1 start). (5) Unproven on dirt surface (1 start). (6) Trip note from last race: Forced pace; vied;game. (7) Stepping up to $40,000 — highest class level in last 10 starts (previous high: $30,000).
Mod1(W): 53 (5/7) Mod2(W): 59 (5/7) Mod3(W): 64 (5/7) Mod1-LS: 13 (6/7) Mod2-LS: 56 (5/7) Mod3-LS: 38 (6/7) Mod4(Form): 60 (5/7) Win Prob: 47.9% Value Score: 3.75 ★ ML: 5.00 (4/1) Overlay %: -0.43 Fair Odds: 7.10 (6/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | C | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | C |
| Early Pace | B | C |
| Mid Pace | D | D |
| Late Pace | B | A |
| Finish Pos | B | A |
| Dirt Speed | D | C |
| Turf Speed | D | D |
| Distance Speed | C | C |
| Trainer Effectiveness | D | B |
| Jockey Effectiveness | D | C |
| 3rd Party Ratings | C | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | C |
| Early Pace | B | C |
| Mid Pace | D | D |
| Late Pace | B | B |
| Sprint FPS | A | A |
| Route FPS | A | A |
| Trainer Effectiveness | D | B |
| Jockey Effectiveness | D | C |
| 3rd Party Ratings | C | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | C |
| Early Pace | F | F |
| Mid Pace | F | F |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 31-day layoff with a recent workout. (2) Hot trainer - high ITM rate (46%). (3) Career-best speed figure (72) recorded in last 1-2 starts — peaking form. (4) Closer/presser in a race with pace pressure — ideal race setup for late runners. (5) Had documented trouble last race (codes: ['D', 'L']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 31 days. (2) Rising in class today ($25,000 → $40,000). (3) First time at today's distance. (4) Moving from a sprint to a route today. (5) Today's distance is longer than any previous start. (6) Unproven on dirt surface (1 start). (7) Trip note from last race: 3w 1/4; mild gain. (8) Rising in class ($25,000 → $40,000) after finishing 3 last out — double negative. (9) Stepping up to $40,000 — highest class level in last 10 starts (previous high: $25,000).
Mod1(W): 26 (7/7) Mod2(W): 44 (6/7) Mod3(W): 26 (7/7) Mod1-LS: 69 (2/7) Mod2-LS: 36 (6/7) Mod3-LS: 42 (4/7) Mod4(Form): 25 (6/7) Win Prob: 36.7% Value Score: 4.31 ★ ML: 8.00 (7/1) Overlay %: 2.99 Fair Odds: 7.69 (7/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | C |
| Early Pace | B | C |
| Mid Pace | A | B |
| Late Pace | B | B |
| Finish Pos | B | A |
| Dirt Speed | B | C |
| Turf Speed | D | D |
| Distance Speed | D | F |
| Trainer Effectiveness | A | B |
| Jockey Effectiveness | C | C |
| 3rd Party Ratings | D | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | C |
| Early Pace | B | C |
| Mid Pace | A | B |
| Late Pace | C | B |
| Sprint FPS | F | D |
| Route FPS | F | D |
| Trainer Effectiveness | A | B |
| Jockey Effectiveness | C | C |
| 3rd Party Ratings | D | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | C |
| Early Pace | F | F |
| Mid Pace | F | F |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 64-day layoff with a recent workout. (2) Hot trainer - high ITM rate (46%). (3) Career-best speed figure (56) recorded in last 1-2 starts — peaking form. (4) Hot jockey — high ITM rate (46%). (5) Switching turf-to-dirt with a strong turf pedigree rating (110) — pedigree suggests main-track improvement is likely. (6) Dropping in class ($40,000 vs last $50,000) after a 64-day freshening — trainer setup-for-win angle. (7) Last race E1 pace (85.0) was 5.2 pts above personal avg (79.8) and horse still finished 5th — pace collapse victim; expect bounce if today's fractions are softer.
⚠ Concerns:(1) Has not raced in 64 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Unproven on dirt surface (2 starts). (4) Switching from turf to dirt today. (5) Poor record at this distance (0 wins from 4 recent starts). (6) Trip note from last race: 4w1T;3-2p far;wknd str. (7) First start at PRX — never raced here before (last seen at: GP).
Mod1(W): 71 (2/7) Mod2(W): 91 (2/7) Mod3(W): 82 (3/7) Mod1-LS: 31 (5/7) Mod2-LS: 87 (2/7) Mod3-LS: 41 (5/7) Mod4(Form): 100 (1/7) Win Prob: 63.3% Value Score: 3.3 ★ ML: 3.00 (2/1) Overlay %: -4.77 Fair Odds: 5.95 (5/1) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | C |
| Early Pace | C | C |
| Mid Pace | B | C |
| Late Pace | D | C |
| Finish Pos | B | A |
| Dirt Speed | F | D |
| Turf Speed | A | B |
| Distance Speed | D | F |
| Trainer Effectiveness | A | B |
| Jockey Effectiveness | B | B |
| 3rd Party Ratings | B | B |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | B |
| Early Pace | B | C |
| Mid Pace | B | C |
| Late Pace | D | C |
| Sprint FPS | B | B |
| Route FPS | A | A |
| Trainer Effectiveness | A | B |
| Jockey Effectiveness | B | B |
| 3rd Party Ratings | B | B |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | C |
| Early Pace | B | C |
| Mid Pace | B | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Had documented trouble last race (codes: ['B', 'D', 'L', 'T', 'U']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Rising in class today ($20,000 → $40,000). (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Speed average (65) well below field median (70). (4) Limited experience at today's distance (2 starts). (5) Moving from a sprint to a route today. (6) Trip note from last race: Rail trip; bid; caught. (7) Dropping in class in consecutive starts ($40,000 → $30,000 → $20,000). (8) Post 7 in a 8-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (9) 0 wins from 5 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 27 (6/7) Mod2(W): 37 (7/7) Mod3(W): 49 (6/7) Mod1-LS: 44 (3/7) Mod2-LS: 32 (7/7) Mod3-LS: 59 (2/7) Mod4(Form): 24 (7/7) Win Prob: 37.6% Value Score: 4.41 ★ ML: 8.00 (7/1) Overlay %: 3.37 Fair Odds: 7.41 (6/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | F | D |
| Early Pace | A | C |
| Mid Pace | A | C |
| Late Pace | F | D |
| Finish Pos | B | A |
| Dirt Speed | D | C |
| Turf Speed | D | D |
| Distance Speed | C | C |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | D | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | C |
| Early Pace | A | B |
| Mid Pace | A | B |
| Late Pace | F | C |
| Sprint FPS | B | B |
| Route FPS | B | B |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | D | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | D |
| Early Pace | A | C |
| Mid Pace | A | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 220-day layoff with a recent workout. (2) Speed average (80) well above field median (70). (3) Career-best speed figure (88) recorded in last 1-2 starts — peaking form. (4) Hot jockey — high ITM rate (48%). (5) Has a bullet work (fastest at track that day) — sharp conditioning signal. (6) Late pace significantly above field median (LP: 91 vs field 77). (7) Closer/presser in a race with pace pressure — ideal race setup for late runners. (8) Returning from 220-day layoff with a bullet workout — trainer signaling extra readiness for today's spot.
⚠ Concerns:(1) Has not raced in 220 days. (2) Poor record at this distance (0 wins from 8 recent starts). (3) Trip note from last race: Broke rein; bolt;eased. (4) Post 8 in a 8-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (5) 0 wins from 8 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 100 (1/7) Mod2(W): 100 (1/7) Mod3(W): 100 (1/7) Mod1-LS: 100 (1/7) Mod2-LS: 100 (1/7) Mod3-LS: 100 (1/7) Mod4(Form): 89 (2/7) Win Prob: 52.5% Value Score: 3.08 ★ ML: 3.50 (5/2) Overlay %: -3.15 Fair Odds: 6.20 (5/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | A |
| Early Pace | F | D |
| Mid Pace | C | D |
| Late Pace | A | A |
| Finish Pos | B | A |
| Dirt Speed | A | A |
| Turf Speed | D | D |
| Distance Speed | A | A |
| Trainer Effectiveness | C | B |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | B |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | B |
| Early Pace | D | D |
| Mid Pace | C | D |
| Late Pace | A | A |
| Sprint FPS | D | D |
| Route FPS | D | C |
| Trainer Effectiveness | C | B |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | B |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | B |
| Early Pace | D | D |
| Mid Pace | C | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Early pace significantly above field median (E1: 90 vs field 86). (2) Fourth race back from a 76-day layoff — often the peak fitness race. (3) Strong speed 2 back (83), modest dip last out (71) — form reversal angle, ready to bounce back to top form. (4) Carries 5 lbs less than field median (117 lbs vs median 122 lbs). (5) Career-best figure (91) buried in races 4–10 back — 10 pts above race median and 8 pts above recent form — market has forgotten the peak effort.
⚠ Concerns:(1) Consider there will be likely pace pressure in this race - multiple E types entered. (2) Speed average (75) well below field median (81). (3) Poor record at this distance (0 wins from 8 recent starts). (4) Trip note from last race: Vied 3-2w; faded. (5) Has not won in last 10 starts despite career wins. (6) 0 wins from 9 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 0 Mod2(W): 0 Mod3(W): 5 (5/5) Mod1-LS: 29 (4/5) Mod2-LS: 0 Mod3-LS: 11 (4/5) Mod4(Form): 0 Win Prob: 23.5% Value Score: 3.71 ★ ML: 12.00 (10/1) Overlay %: 8.44 Fair Odds: 5.76 (5/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | F | B |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | F | C |
| Finish Pos | F | F |
| Dirt Speed | A | A |
| Turf Speed | C | B |
| Distance Speed | A | A |
| Trainer Effectiveness | F | C |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | D | B |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | B |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | F | D |
| Sprint FPS | A | A |
| Route FPS | A | A |
| Trainer Effectiveness | F | C |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | D | B |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | B |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Closer/presser in a race with pace pressure — ideal race setup for late runners. (2) Has won at today's distance (1320 yds) within the last 10 starts — proven ability at this trip. (3) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (4) Trainer 'GUERRERO J GUADALUPE' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (5) Had documented trouble last race (codes: ['B', 'D', 'L', 'T']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Trip note from last race: Btwn; wide; willingly. (2) No workout in last 30 days despite 24 days since last race.
Mod1(W): 37 (3/5) Mod2(W): 34 (3/5) Mod3(W): 42 (3/5) Mod1-LS: 23 (5/5) Mod2-LS: 42 (3/5) Mod3-LS: 1 (5/5) Mod4(Form): 55 (3/5) Win Prob: 57.2% Value Score: 3.81 ★ ML: 4.50 (7/2) Overlay %: 2.23 Fair Odds: 4.80 (4/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | A |
| Early Pace | C | B |
| Mid Pace | D | B |
| Late Pace | A | A |
| Finish Pos | C | B |
| Dirt Speed | D | A |
| Turf Speed | D | D |
| Distance Speed | B | A |
| Trainer Effectiveness | C | A |
| Jockey Effectiveness | C | C |
| 3rd Party Ratings | C | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | A |
| Early Pace | C | B |
| Mid Pace | D | A |
| Late Pace | B | A |
| Sprint FPS | D | B |
| Route FPS | F | C |
| Trainer Effectiveness | C | A |
| Jockey Effectiveness | C | C |
| 3rd Party Ratings | C | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | B |
| Early Pace | C | B |
| Mid Pace | C | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Hot trainer - high ITM rate (60%). (2) Career-best speed figure (98) recorded in last 1-2 starts — peaking form. (3) Hot jockey — high ITM rate (48%). (4) Won last 2 consecutive starts. (5) Late pace significantly above field median (LP: 86 vs field 83). (6) Strong speed 2 back (98), modest dip last out (90) — form reversal angle, ready to bounce back to top form. (7) Has won at today's distance (1320 yds) within the last 10 starts — proven ability at this trip. (8) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (9) Trainer 'NESS JAMIE' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (10) Had documented trouble last race (codes: ['B', 'D', 'L', 'T', 'U']) yet still finished 1st — a clean trip today sets up a form reversal. (11) Averages 85.0 speed pts in today's distance/surface configuration vs 78.2 in other configs (6 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Consider there will be likely pace pressure in this race - multiple E types entered. (2) Trip note from last race: Waited turn; rail bid. (3) Consistently breaks behind post position (3 of last 5 starts). (4) No workout in last 30 days despite 26 days since last race. (5) Speed figures are highly erratic over last 5 starts (σ = 10.7 pts: [90, 98, 93, 70, 85]) — unpredictable performer.
Mod1(W): 100 (1/5) Mod2(W): 100 (1/5) Mod3(W): 100 (1/5) Mod1-LS: 100 (1/5) Mod2-LS: 100 (1/5) Mod3-LS: 100 (1/5) Mod4(Form): 100 (1/5) Win Prob: 72.4% Value Score: 2.28 ★ ML: 1.60 (3/5) Overlay %: -12.55 Fair Odds: 4.20 (3/1) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | A |
| Early Pace | F | C |
| Mid Pace | F | B |
| Late Pace | A | A |
| Finish Pos | A | A |
| Dirt Speed | A | A |
| Turf Speed | B | A |
| Distance Speed | F | B |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | A |
| Early Pace | C | B |
| Mid Pace | C | A |
| Late Pace | A | A |
| Sprint FPS | C | A |
| Route FPS | B | A |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | A |
| Early Pace | D | B |
| Mid Pace | D | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Hot trainer - high ITM rate (60%). (2) Closer/presser in a race with pace pressure — ideal race setup for late runners. (3) Has won at today's distance (1320 yds) within the last 10 starts — proven ability at this trip. (4) Trainer 'PADILLA-PRECIADO ERNESTO' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (5) Career-best figure (90) buried in races 4–10 back — 9 pts above race median and 7 pts above recent form — market has forgotten the peak effort. (6) Had documented trouble last race (codes: ['D', 'L', 'S', 'T']) yet still finished 4th — a clean trip today sets up a form reversal. (7) Averages 82.3 speed pts in today's distance/surface configuration vs 70.0 in other configs (6 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Trip note from last race: Late energy inside. (2) Consistently breaks behind post position (3 of last 5 starts). (3) Consistently runs wide at the first call (3 of last 5 starts). (4) Last race was career-best speed (83) — bounce risk after peak effort. (5) No workout in last 30 days despite 24 days since last race.
Mod1(W): 6 (5/5) Mod2(W): 17 (4/5) Mod3(W): 23 (4/5) Mod1-LS: 0 Mod2-LS: 18 (5/5) Mod3-LS: 0 Mod4(Form): 36 (4/5) Win Prob: 41.7% Value Score: 3.53 ★ ML: 6.00 (5/1) Overlay %: 4.16 Fair Odds: 5.27 (9/2) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | C | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | B |
| Early Pace | D | C |
| Mid Pace | C | B |
| Late Pace | C | A |
| Finish Pos | D | F |
| Dirt Speed | F | B |
| Turf Speed | A | A |
| Distance Speed | D | A |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | B | B |
| 3rd Party Ratings | F | B |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | B |
| Early Pace | F | B |
| Mid Pace | F | B |
| Late Pace | B | A |
| Sprint FPS | F | C |
| Route FPS | D | C |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | B | B |
| 3rd Party Ratings | F | B |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | B |
| Early Pace | F | B |
| Mid Pace | F | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Strong trainer/jockey combo - 5 wins from 15 starts (33%). (2) Has won at today's distance (1320 yds) within the last 10 starts — proven ability at this trip. (3) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (4) Trainer 'PENALOZA MIGUEL' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (5) Had documented trouble last race (codes: ['D', 'L', 'V']) yet still finished 1st — a clean trip today sets up a form reversal. (6) Averages 82.9 speed pts in today's distance/surface configuration vs 77.0 in other configs (7 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Rising in class today ($12,500 → $25,000). (2) Was claimed from its most recent race - new connections. (3) Consider there will be likely pace pressure in this race - multiple E types entered. (4) Trip note from last race: Pace; clear; driving. (5) No workout in last 30 days despite 18 days since last race.
Mod1(W): 12 (4/5) Mod2(W): 12 (5/5) Mod3(W): 0 Mod1-LS: 90 (2/5) Mod2-LS: 20 (4/5) Mod3-LS: 26 (2/5) Mod4(Form): 9 (5/5) Win Prob: 17.3% Value Score: 2.31 ★ ML: 10.00 (9/1) Overlay %: 7.24 Fair Odds: 5.78 (5/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | F | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | A |
| Early Pace | B | B |
| Mid Pace | B | A |
| Late Pace | D | A |
| Finish Pos | B | B |
| Dirt Speed | B | A |
| Turf Speed | A | A |
| Distance Speed | C | A |
| Trainer Effectiveness | D | C |
| Jockey Effectiveness | F | D |
| 3rd Party Ratings | B | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | B |
| Early Pace | C | B |
| Mid Pace | A | A |
| Late Pace | D | C |
| Sprint FPS | A | A |
| Route FPS | C | B |
| Trainer Effectiveness | D | C |
| Jockey Effectiveness | F | D |
| 3rd Party Ratings | B | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | A |
| Early Pace | B | B |
| Mid Pace | B | A |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Strong trainer/jockey combo - 28 wins from 67 starts (42%). (2) Hot jockey — high ITM rate (52%). (3) In the money in last 4 consecutive starts. (4) Early pace significantly above field median (E1: 91 vs field 86). (5) Has won at today's distance (1320 yds) within the last 10 starts — proven ability at this trip. (6) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (7) Trainer 'PINO MICHAEL V' has 4 horses in today's card all showing last-race improvement — barn appears sharp right now. (8) Had documented trouble last race (codes: ['D', 'L', 'O']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Consider there will be likely pace pressure in this race - multiple E types entered. (2) Trip note from last race: Clear; hooked; gamely. (3) Last race was career-best speed (88) — bounce risk after peak effort. (4) Stepping up to $25,000 — highest class level in last 10 starts (previous high: $10,000).
Mod1(W): 63 (2/5) Mod2(W): 79 (2/5) Mod3(W): 70 (2/5) Mod1-LS: 81 (3/5) Mod2-LS: 81 (2/5) Mod3-LS: 18 (3/5) Mod4(Form): 93 (2/5) Win Prob: 44.1% Value Score: 1.6 ★ ML: 2.00 (1/1) Overlay %: -9.51 Fair Odds: 4.55 (7/2) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | A |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | B | A |
| Finish Pos | A | A |
| Dirt Speed | C | A |
| Turf Speed | D | D |
| Distance Speed | A | A |
| Trainer Effectiveness | B | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | A |
| Early Pace | A | A |
| Mid Pace | B | A |
| Late Pace | C | A |
| Sprint FPS | B | A |
| Route FPS | A | A |
| Trainer Effectiveness | B | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | A |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Strong trainer/jockey combo - 4 wins from 7 starts (57%). (2) Hot jockey — high ITM rate (52%). (3) Track specialist — 2 wins from 5 starts here (40%). (4) Strong speed 2 back (83), modest dip last out (74) — form reversal angle, ready to bounce back to top form. (5) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip. (6) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (7) Career-best figure (89) buried in races 4–10 back — 19 pts above race median and 6 pts above recent form — market has forgotten the peak effort. (8) Had documented trouble last race (codes: ['B', 'D', 'L', 'S', 'T', 'U']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Consider there will be likely pace pressure in this race - multiple E types entered. (2) Trip note from last race: Stumbled st; wait 5/16. (3) No workout in last 30 days despite 17 days since last race. (4) Speed figures are highly erratic over last 5 starts (σ = 8.7 pts: [74, 83, 67, 83, 89]) — unpredictable performer.
Mod1(W): 62 (4/5) Mod2(W): 72 (2/5) Mod3(W): 98 (2/5) Mod1-LS: 51 (2/5) Mod2-LS: 71 (3/5) Mod3-LS: 100 (1/5) Mod4(Form): 91 (2/5) Win Prob: 66% Value Score: 3.14 ★ ML: 3.00 (2/1) Overlay %: -2.97 Fair Odds: 4.55 (7/2) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | C |
| Early Pace | D | B |
| Mid Pace | D | B |
| Late Pace | B | C |
| Finish Pos | B | B |
| Dirt Speed | A | A |
| Turf Speed | C | D |
| Distance Speed | A | A |
| Trainer Effectiveness | C | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | B | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | B |
| Early Pace | D | B |
| Mid Pace | C | A |
| Late Pace | B | C |
| Sprint FPS | C | B |
| Route FPS | D | B |
| Trainer Effectiveness | C | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | B | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | D |
| Early Pace | C | B |
| Mid Pace | D | A |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 123-day layoff with a recent workout. (2) Big last-race effort (71) — 9 pts above recent average. (3) Equipment change today (code: 1). (4) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip. (5) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (6) Had documented trouble last race (codes: ['D', 'L', 'O', 'S', 'T', 'U']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 123 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Speed average (64) well below field median (70). (4) Trip note from last race: Slow start; wide rush. (5) Last race was career-best speed (71) — bounce risk after peak effort.
Mod1(W): 58 (5/5) Mod2(W): 25 (5/5) Mod3(W): 51 (5/5) Mod1-LS: 9 (5/5) Mod2-LS: 37 (5/5) Mod3-LS: 27 (5/5) Mod4(Form): 60 (4/5) Win Prob: 38.5% Value Score: 2.52 ★ ML: 4.50 (7/2) Overlay %: 0.76 Fair Odds: 5.24 (4/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | C | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | F | D |
| Early Pace | A | A |
| Mid Pace | C | A |
| Late Pace | D | D |
| Finish Pos | F | C |
| Dirt Speed | F | C |
| Turf Speed | C | D |
| Distance Speed | F | F |
| Trainer Effectiveness | D | B |
| Jockey Effectiveness | C | C |
| 3rd Party Ratings | D | B |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | D |
| Early Pace | A | A |
| Mid Pace | B | A |
| Late Pace | F | D |
| Sprint FPS | A | A |
| Route FPS | B | A |
| Trainer Effectiveness | D | B |
| Jockey Effectiveness | C | C |
| 3rd Party Ratings | D | B |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | D |
| Early Pace | A | A |
| Mid Pace | C | A |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 45-day layoff with a recent workout. (2) Hot trainer - high ITM rate (59%). (3) Big last-race effort (78) — 14 pts above recent average. (4) In the money in last 4 consecutive starts. (5) Early pace significantly above field median (E1: 95 vs field 92). (6) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip. (7) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (8) Trainer 'PINO MICHAEL V' has 4 horses in today's card all showing last-race improvement — barn appears sharp right now. (9) Had documented trouble last race (codes: ['D', 'L', 'V']) yet still finished 1st — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 45 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Speed average (64) well below field median (70). (4) Trip note from last race: Clear; wdnd; driving. (5) Last race was career-best speed (78) — bounce risk after peak effort. (6) Speed figures are highly erratic over last 5 starts (σ = 10.2 pts: [78, 62, 70, 61, 51]) — unpredictable performer.
Mod1(W): 85 (2/5) Mod2(W): 65 (3/5) Mod3(W): 69 (3/5) Mod1-LS: 22 (4/5) Mod2-LS: 78 (2/5) Mod3-LS: 72 (3/5) Mod4(Form): 60 (5/5) Win Prob: 43.2% Value Score: 2.83 ★ ML: 4.50 (7/2) Overlay %: 1.53 Fair Odds: 4.95 (4/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | D |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | F | D |
| Finish Pos | C | B |
| Dirt Speed | D | B |
| Turf Speed | C | D |
| Distance Speed | C | B |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | F | D |
| 3rd Party Ratings | A | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | C |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | D | D |
| Sprint FPS | A | A |
| Route FPS | A | A |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | F | D |
| 3rd Party Ratings | A | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | D |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Hot trainer - high ITM rate (60%). (2) Has a bullet work (fastest at track that day) — sharp conditioning signal. (3) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip. (4) Returning from 33-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (5) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (6) Trainer 'PADILLA-PRECIADO ERNESTO' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (7) Had documented trouble last race (codes: ['D', 'L', 'S', 'U']) yet still finished 1st — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 33 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Limited experience at today's distance (2 starts). (4) Unproven on dirt surface (2 starts). (5) Trip note from last race: Pursued; held gamely. (6) Last race was career-best speed (80) — bounce risk after peak effort.
Mod1(W): 67 (3/5) Mod2(W): 59 (4/5) Mod3(W): 64 (4/5) Mod1-LS: 32 (3/5) Mod2-LS: 68 (4/5) Mod3-LS: 94 (2/5) Mod4(Form): 69 (3/5) Win Prob: 59.5% Value Score: 3.54 ★ ML: 4.00 (3/1) Overlay %: 0.17 Fair Odds: 4.89 (4/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | B |
| Early Pace | C | A |
| Mid Pace | A | A |
| Late Pace | C | C |
| Finish Pos | A | A |
| Dirt Speed | C | B |
| Turf Speed | C | D |
| Distance Speed | B | B |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | B | B |
| 3rd Party Ratings | C | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | B |
| Early Pace | C | A |
| Mid Pace | A | A |
| Late Pace | C | C |
| Sprint FPS | D | C |
| Route FPS | A | A |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | B | B |
| 3rd Party Ratings | C | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | A |
| Early Pace | D | B |
| Mid Pace | B | A |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 32-day layoff with a recent workout. (2) Speed average (80) well above field median (70). (3) Significantly better on off tracks (off: 92 vs fast: 82). (4) Career-best speed figure (82) recorded in last 1-2 starts — peaking form. (5) Hot jockey — high ITM rate (46%). (6) Track specialist — 2 wins from 5 starts here (40%). (7) Late pace significantly above field median (LP: 79 vs field 73). (8) Fourth race back from a 65-day layoff — often the peak fitness race. (9) Strong speed 2 back (92), modest dip last out (82) — form reversal angle, ready to bounce back to top form. (10) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip. (11) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (12) Had documented trouble last race (codes: ['D', 'L', 'O', 'T', 'U', 'V']) yet still finished 4th — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 32 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Trip note from last race: Vied early; outkicked.
Mod1(W): 100 (1/5) Mod2(W): 100 (1/5) Mod3(W): 100 (1/5) Mod1-LS: 100 (1/5) Mod2-LS: 100 (1/5) Mod3-LS: 0 Mod4(Form): 100 (1/5) Win Prob: 38.1% Value Score: 1.59 ★ ML: 2.50 (3/2) Overlay %: -4.44 Fair Odds: 4.11 (3/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | A |
| Early Pace | B | A |
| Mid Pace | B | A |
| Late Pace | A | B |
| Finish Pos | A | B |
| Dirt Speed | B | B |
| Turf Speed | C | D |
| Distance Speed | A | A |
| Trainer Effectiveness | B | A |
| Jockey Effectiveness | A | B |
| 3rd Party Ratings | A | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | A |
| Early Pace | B | A |
| Mid Pace | D | A |
| Late Pace | A | A |
| Sprint FPS | B | B |
| Route FPS | C | B |
| Trainer Effectiveness | B | A |
| Jockey Effectiveness | A | B |
| 3rd Party Ratings | A | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | B |
| Early Pace | B | A |
| Mid Pace | A | A |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Track specialist — 2 wins from 7 starts here (29%). (2) Closer/presser in a race with pace pressure — ideal race setup for late runners. (3) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip. (4) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (5) Trainer 'GONZALEZ-MILIAN JOSE G' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now.
⚠ Concerns:(1) Trip note from last race: Off slowly; steadied. (2) Consistently runs wide at the first call (3 of last 5 starts). (3) No workout in last 30 days despite 17 days since last race. (4) Stepping up to $75,000 — highest class level in last 10 starts (previous high: $40,000). (5) Speed figures are highly erratic over last 5 starts (σ = 11.1 pts: [62, 73, 85, 56, 69]) — unpredictable performer.
Mod1(W): 0 Mod2(W): 0 Mod3(W): 0 Mod1-LS: 0 Mod2-LS: 0 Mod3-LS: 53 (4/5) Mod4(Form): 0 Win Prob: 40.3% Value Score: 5.28 ★ ML: 10.00 (9/1) Overlay %: 4.95 Fair Odds: 6.94 (6/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | F | D |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | C |
| Early Pace | F | C |
| Mid Pace | F | C |
| Late Pace | A | C |
| Finish Pos | D | C |
| Dirt Speed | A | A |
| Turf Speed | C | D |
| Distance Speed | D | C |
| Trainer Effectiveness | F | D |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | F | B |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | B |
| Early Pace | F | C |
| Mid Pace | F | B |
| Late Pace | A | B |
| Sprint FPS | F | D |
| Route FPS | F | D |
| Trainer Effectiveness | F | D |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | F | B |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | C |
| Early Pace | F | C |
| Mid Pace | F | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Hot trainer - high ITM rate (63%). (2) Fourth race back from a 53-day layoff — often the peak fitness race. (3) Has won at today's distance (1830 yds) within the last 10 starts — proven ability at this trip. (4) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (5) Last race E1 pace (87.0) was 5.1 pts above personal avg (81.9) and horse still finished 7th — pace collapse victim; expect bounce if today's fractions are softer.
⚠ Concerns:(1) Has not raced in 31 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) 0 wins from 7 career starts on off tracks. (4) Trip note from last race: Rated outside; empty. (5) 0 wins from post 1 in 3 recent starts. (6) No workout in last 30 days despite 31 days since last race.
Mod1(W): 2 (7/7) Mod2(W): 6 (6/7) Mod3(W): 9 (6/7) Mod1-LS: 89 (2/7) Mod2-LS: 0 (6/7) Mod3-LS: 71 (3/7) Mod4(Form): 5 (6/7) Win Prob: 25.4% Value Score: 3.56 ★ ML: 10.00 (9/1) Overlay %: 4.80 Fair Odds: 7.39 (6/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | A |
| Early Pace | B | C |
| Mid Pace | D | B |
| Late Pace | D | A |
| Finish Pos | B | C |
| Dirt Speed | B | A |
| Turf Speed | D | D |
| Distance Speed | A | A |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | D | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | B |
| Early Pace | D | C |
| Mid Pace | D | B |
| Late Pace | C | B |
| Sprint FPS | A | B |
| Route FPS | D | C |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | D | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | B |
| Early Pace | C | C |
| Mid Pace | D | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 46-day layoff with a recent workout. (2) Closer/presser in a race with pace pressure — ideal race setup for late runners. (3) Has won at today's distance (1830 yds) within the last 10 starts — proven ability at this trip. (4) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (5) Speed improved +11 pts then +5 pts in last 2 starts (69 → 80 → 85) — trainer is progressively building fitness. (6) Trainer 'GONZALEZ-MILIAN JOSE G' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (7) Had documented trouble last race (codes: ['B', 'D', 'F', 'L', 'O', 'S', 'U']) yet still finished 3rd — a clean trip today sets up a form reversal. (8) Averages 81.1 speed pts in today's distance/surface configuration vs 70.7 in other configs (7 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Has not raced in 46 days. (2) Trip note from last race: Off slowly; bumped. (3) Stepping up to $50,000 — highest class level in last 10 starts (previous high: $25,000). (4) Two consecutive 5+ pt speed jumps (69 → 80 → 85) and last race speed is well above career average (78) — high bounce risk after back-to-back peak efforts.
Mod1(W): 23 (6/7) Mod2(W): 3 (7/7) Mod3(W): 0 Mod1-LS: 74 (4/7) Mod2-LS: 0 Mod3-LS: 28 (6/7) Mod4(Form): 5 (7/7) Win Prob: 37.5% Value Score: 5.26 ★ ML: 10.00 (9/1) Overlay %: 3.75 Fair Odds: 8.20 (7/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | F | D |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | B |
| Early Pace | F | D |
| Mid Pace | F | C |
| Late Pace | C | A |
| Finish Pos | A | B |
| Dirt Speed | F | A |
| Turf Speed | B | C |
| Distance Speed | C | A |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | C | D |
| 3rd Party Ratings | C | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | B |
| Early Pace | C | C |
| Mid Pace | B | A |
| Late Pace | D | C |
| Sprint FPS | D | D |
| Route FPS | B | B |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | C | D |
| 3rd Party Ratings | C | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | B |
| Early Pace | B | B |
| Mid Pace | F | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 31-day layoff with a recent workout. (2) Big last-race effort (89) — 15 pts above recent average. (3) Hot jockey — high ITM rate (46%). (4) Early pace significantly above field median (E1: 92 vs field 82). (5) Fourth race back from a 50-day layoff — often the peak fitness race. (6) Returning from 31-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (7) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (8) Trainer 'SERVIS J TYLER' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (9) Had documented trouble last race (codes: ['D', 'L', 'S', 'T']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 31 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Limited experience at today's distance (1 start). (4) Trip note from last race: Wide; led; resisted.
Mod1(W): 39 (5/7) Mod2(W): 38 (4/7) Mod3(W): 47 (4/7) Mod1-LS: 0 Mod2-LS: 30 (4/7) Mod3-LS: 58 (4/7) Mod4(Form): 34 (4/7) Win Prob: 27.6% Value Score: 2.47 ★ ML: 6.00 (5/1) Overlay %: 1.39 Fair Odds: 6.95 (6/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | C | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | A |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | F | B |
| Finish Pos | C | C |
| Dirt Speed | C | A |
| Turf Speed | D | D |
| Distance Speed | C | A |
| Trainer Effectiveness | B | A |
| Jockey Effectiveness | A | B |
| 3rd Party Ratings | B | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | B |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | F | C |
| Sprint FPS | A | B |
| Route FPS | A | B |
| Trainer Effectiveness | B | A |
| Jockey Effectiveness | A | B |
| 3rd Party Ratings | B | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | B |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Dropping in class today ($100,000 → $50,000). (2) Hot trainer - high ITM rate (60%). (3) Strong trainer/jockey combo - 13 wins from 42 starts (31%). (4) Career-best speed figure (91) recorded in last 1-2 starts — peaking form. (5) Hot jockey — high ITM rate (52%). (6) In the money in last 8 consecutive starts. (7) Late pace significantly above field median (LP: 90 vs field 85). (8) Closer/presser in a race with pace pressure — ideal race setup for late runners. (9) Has won at today's distance (1830 yds) within the last 10 starts — proven ability at this trip. (10) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (11) Trainer 'NESS JAMIE' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (12) Had documented trouble last race (codes: ['D', 'L', 'S', 'T']) yet still finished 3rd — a clean trip today sets up a form reversal. (13) Averages 88.0 speed pts in today's distance/surface configuration vs 82.6 in other configs (3 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Moving from a sprint to a route today. (2) 0 wins from 4 career starts on off tracks. (3) Trip note from last race: Stalked 3w; held 3rd. (4) Consistently breaks behind post position (3 of last 5 starts). (5) No workout in last 30 days despite 18 days since last race.
Mod1(W): 100 (1/7) Mod2(W): 100 (1/7) Mod3(W): 100 (1/7) Mod1-LS: 100 (1/7) Mod2-LS: 100 (1/7) Mod3-LS: 100 (1/7) Mod4(Form): 100 (1/7) Win Prob: 62.4% Value Score: 2.39 ★ ML: 2.00 (1/1) Overlay %: -11.22 Fair Odds: 5.72 (9/2) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | A |
| Early Pace | C | D |
| Mid Pace | B | B |
| Late Pace | A | A |
| Finish Pos | A | B |
| Dirt Speed | D | A |
| Turf Speed | A | A |
| Distance Speed | B | A |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | A |
| Early Pace | D | D |
| Mid Pace | D | B |
| Late Pace | A | A |
| Sprint FPS | C | C |
| Route FPS | A | B |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | A |
| Early Pace | D | C |
| Mid Pace | B | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 31-day layoff with a recent workout. (2) Early pace significantly above field median (E1: 86 vs field 82). (3) Has won at today's distance (1830 yds) within the last 10 starts — proven ability at this trip. (4) Trainer 'PENALOZA MIGUEL' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (5) Career-best figure (100) buried in races 4–10 back — 19 pts above race median and 12 pts above recent form — market has forgotten the peak effort. (6) Had documented trouble last race (codes: ['D', 'L', 'O', 'S', 'T']) yet still finished 3rd — a clean trip today sets up a form reversal. (7) Averages 86.1 speed pts in today's distance/surface configuration vs 80.0 in other configs (8 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Has not raced in 31 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) 0 wins from 4 career starts on off tracks. (4) Trip note from last race: Rail trip; closed well. (5) Speed figures are highly erratic over last 5 starts (σ = 9.4 pts: [88, 78, 77, 100, 89]) — unpredictable performer.
Mod1(W): 53 (3/7) Mod2(W): 48 (3/7) Mod3(W): 53 (3/7) Mod1-LS: 7 (7/7) Mod2-LS: 39 (3/7) Mod3-LS: 26 (7/7) Mod4(Form): 45 (3/7) Win Prob: 28.8% Value Score: 2.21 ★ ML: 5.00 (4/1) Overlay %: 0.14 Fair Odds: 6.58 (6/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | A |
| Early Pace | A | B |
| Mid Pace | A | A |
| Late Pace | B | A |
| Finish Pos | B | B |
| Dirt Speed | A | A |
| Turf Speed | D | D |
| Distance Speed | A | A |
| Trainer Effectiveness | C | C |
| Jockey Effectiveness | B | B |
| 3rd Party Ratings | A | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | A |
| Early Pace | B | B |
| Mid Pace | A | A |
| Late Pace | B | B |
| Sprint FPS | B | C |
| Route FPS | C | C |
| Trainer Effectiveness | C | C |
| Jockey Effectiveness | B | B |
| 3rd Party Ratings | A | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | A |
| Early Pace | A | B |
| Mid Pace | A | A |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 31-day layoff with a recent workout. (2) Hot trainer - high ITM rate (57%). (3) Big last-race effort (92) — 9 pts above recent average. (4) Hot jockey — high ITM rate (46%). (5) In the money in last 3 consecutive starts. (6) Late pace significantly above field median (LP: 88 vs field 85). (7) Closer/presser in a race with pace pressure — ideal race setup for late runners. (8) Fourth race back from a 82-day layoff — often the peak fitness race. (9) Has won at today's distance (1830 yds) within the last 10 starts — proven ability at this trip. (10) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (11) Had documented trouble last race (codes: ['B', 'D']) yet still finished 1st — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 31 days. (2) Trip note from last race: Wide bid; edged away. (3) Last race was career-best speed (92) — bounce risk after peak effort.
Mod1(W): 74 (2/7) Mod2(W): 81 (2/7) Mod3(W): 75 (2/7) Mod1-LS: 82 (3/7) Mod2-LS: 82 (2/7) Mod3-LS: 0 Mod4(Form): 81 (2/7) Win Prob: 40.7% Value Score: 2.08 ★ ML: 3.00 (2/1) Overlay %: -5.51 Fair Odds: 6.11 (5/1) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | A |
| Early Pace | D | D |
| Mid Pace | C | B |
| Late Pace | B | A |
| Finish Pos | D | C |
| Dirt Speed | D | A |
| Turf Speed | A | A |
| Distance Speed | B | A |
| Trainer Effectiveness | B | A |
| Jockey Effectiveness | B | B |
| 3rd Party Ratings | B | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | A |
| Early Pace | B | C |
| Mid Pace | C | B |
| Late Pace | B | A |
| Sprint FPS | D | D |
| Route FPS | D | C |
| Trainer Effectiveness | B | A |
| Jockey Effectiveness | B | B |
| 3rd Party Ratings | B | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | A |
| Early Pace | F | D |
| Mid Pace | C | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Big last-race effort (82) — 13 pts above recent average. (2) Has a bullet work (fastest at track that day) — sharp conditioning signal. (3) Closer/presser in a race with pace pressure — ideal race setup for late runners. (4) Fourth race back from a 50-day layoff — often the peak fitness race. (5) Career-best figure (92) buried in races 4–10 back — 11 pts above race median and 10 pts above recent form — market has forgotten the peak effort. (6) Had documented trouble last race (codes: ['F', 'L', 'O', 'T']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) First time at today's distance. (2) Moving from a sprint to a route today. (3) Today's distance is longer than any previous start. (4) 0 wins from 4 career starts on off tracks. (5) Trip note from last race: Rail trip; game effort. (6) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 40 (4/7) Mod2(W): 11 (5/7) Mod3(W): 14 (5/7) Mod1-LS: 69 (5/7) Mod2-LS: 3 (5/7) Mod3-LS: 75 (2/7) Mod4(Form): 13 (5/7) Win Prob: 34.7% Value Score: 3.98 ★ ML: 8.00 (7/1) Overlay %: 2.95 Fair Odds: 7.58 (7/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | F | B |
| Early Pace | B | C |
| Mid Pace | B | A |
| Late Pace | D | B |
| Finish Pos | F | F |
| Dirt Speed | A | A |
| Turf Speed | D | D |
| Distance Speed | F | A |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | D | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | C |
| Early Pace | A | B |
| Mid Pace | B | A |
| Late Pace | D | C |
| Sprint FPS | B | C |
| Route FPS | B | B |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | D | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | B |
| Early Pace | B | C |
| Mid Pace | B | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Dropping in class today ($100,000 → $50,000). (2) Late pace significantly above field median (LP: 94 vs field 85). (3) Closer/presser in a race with pace pressure — ideal race setup for late runners. (4) Fourth race back from a 76-day layoff — often the peak fitness race. (5) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo.
⚠ Concerns:(1) Limited experience at today's distance (1 start). (2) Moving from a sprint to a route today. (3) Trip note from last race: Outrun. (4) Consistently runs wide at the first call (3 of last 5 starts). (5) Has not won in last 10 starts despite career wins. (6) No workout in last 30 days despite 18 days since last race.
Mod1(W): 0 Mod2(W): 0 Mod3(W): 3 (7/7) Mod1-LS: 10 (6/7) Mod2-LS: 0 (7/7) Mod3-LS: 48 (5/7) Mod4(Form): 0 Win Prob: 28.8% Value Score: 4.04 ★ ML: 10.00 (9/1) Overlay %: 3.70 Fair Odds: 8.24 (7/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | D |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | A |
| Early Pace | D | D |
| Mid Pace | D | B |
| Late Pace | A | A |
| Finish Pos | D | C |
| Dirt Speed | B | A |
| Turf Speed | B | C |
| Distance Speed | D | A |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | F | F |
| 3rd Party Ratings | F | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | A |
| Early Pace | F | D |
| Mid Pace | F | C |
| Late Pace | A | A |
| Sprint FPS | F | D |
| Route FPS | F | D |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | F | F |
| 3rd Party Ratings | F | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | B |
| Early Pace | F | D |
| Mid Pace | D | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 31-day layoff with a recent workout. (2) Late pace significantly above field median (LP: 82 vs field 74). (3) Closer/presser in a race with pace pressure — ideal race setup for late runners. (4) Had documented trouble last race (codes: ['L']) yet still finished 2nd — a clean trip today sets up a form reversal. (5) Averages 75.7 speed pts in today's distance/surface configuration vs 66.7 in other configs (7 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Has not raced in 31 days. (2) Poor record at this distance (0 wins from 8 recent starts). (3) Poor record at this track (0 wins from 6 starts). (4) Trip note from last race: Rail rally; gamely. (5) Has not won in last 10 starts despite career wins. (6) 0 wins from 8 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 54 (4/12) Mod2(W): 69 (4/12) Mod3(W): 65 (5/12) Mod1-LS: 64 (7/12) Mod2-LS: 68 (4/12) Mod3-LS: 57 (7/12) Mod4(Form): 83 (4/12) Win Prob: 41.1% Value Score: 3.54 ★ ML: 5.00 (4/1) Overlay %: -3.18 Fair Odds: 10.85 (10/1) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | B |
| Early Pace | F | D |
| Mid Pace | F | C |
| Late Pace | A | A |
| Finish Pos | C | F |
| Dirt Speed | A | A |
| Turf Speed | A | A |
| Distance Speed | A | A |
| Trainer Effectiveness | C | D |
| Jockey Effectiveness | B | D |
| 3rd Party Ratings | B | B |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | A |
| Early Pace | D | C |
| Mid Pace | C | B |
| Late Pace | A | A |
| Sprint FPS | D | C |
| Route FPS | C | C |
| Trainer Effectiveness | C | D |
| Jockey Effectiveness | B | D |
| 3rd Party Ratings | B | B |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | C |
| Early Pace | D | C |
| Mid Pace | F | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Hot trainer - high ITM rate (43%). (2) Career-best speed figure (78) recorded in last 1-2 starts — peaking form. (3) Hot jockey — high ITM rate (42%). (4) Has won at today's distance (1210 yds) within the last 10 starts — proven ability at this trip. (5) Returning from 31-day layoff with a bullet workout — trainer signaling extra readiness for today's spot.
⚠ Concerns:(1) Has not raced in 31 days. (2) Was claimed from its most recent race - new connections. (3) Consider there will be likely pace pressure in this race - multiple E types entered. (4) Trip note from last race: Dueled 3-2w; faded. (5) Was the betting favorite in the last race but finished off the board. (6) Has not won in last 10 starts despite career wins. (7) No workout in last 30 days despite 31 days since last race. (8) Speed figures are highly erratic over last 5 starts (σ = 12.1 pts: [56, 78, 73, 51, 74]) — unpredictable performer.
Mod1(W): 52 (5/12) Mod2(W): 56 (5/12) Mod3(W): 76 (3/12) Mod1-LS: 52 (10/12) Mod2-LS: 52 (5/12) Mod3-LS: 42 (9/12) Mod4(Form): 82 (5/12) Win Prob: 34.2% Value Score: 2.94 ★ ML: 5.00 (4/1) Overlay %: -3.26 Fair Odds: 10.97 (10/1) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | C |
| Early Pace | B | B |
| Mid Pace | B | B |
| Late Pace | D | C |
| Finish Pos | B | D |
| Dirt Speed | F | B |
| Turf Speed | F | D |
| Distance Speed | C | B |
| Trainer Effectiveness | A | C |
| Jockey Effectiveness | B | C |
| 3rd Party Ratings | B | B |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | C |
| Early Pace | B | B |
| Mid Pace | B | A |
| Late Pace | D | D |
| Sprint FPS | B | A |
| Route FPS | A | A |
| Trainer Effectiveness | A | C |
| Jockey Effectiveness | B | C |
| 3rd Party Ratings | B | B |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | C |
| Early Pace | B | B |
| Mid Pace | B | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 61-day layoff with a recent workout. (2) Dropping in class today ($7,500 → $5,000). (3) Early pace significantly above field median (E1: 89 vs field 85). (4) Has won at today's distance (1210 yds) within the last 10 starts — proven ability at this trip. (5) Dropping in class ($5,000 vs last $7,500) after a 61-day freshening — trainer setup-for-win angle. (6) Career-best figure (83) buried in races 4–10 back — 13 pts above race median and 13 pts above recent form — market has forgotten the peak effort.
⚠ Concerns:(1) Has not raced in 61 days. (2) Speed average (64) well below field median (70). (3) Trip note from last race: Slow start; stopped. (4) Speed figures are highly erratic over last 5 starts (σ = 30.5 pts: [36, 70, 8, 68, 83]) — unpredictable performer.
Mod1(W): 9 (8/12) Mod2(W): 14 (11/12) Mod3(W): 31 (9/12) Mod1-LS: 51 (11/12) Mod2-LS: 20 (10/12) Mod3-LS: 7 (12/12) Mod4(Form): 21 (8/12) Win Prob: 30.8% Value Score: 7.06 ★ ML: 15.00 (15/1) Overlay %: 2.31 Fair Odds: 13.99 (12/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | F | D |
| Early Pace | B | A |
| Mid Pace | C | B |
| Late Pace | D | C |
| Finish Pos | D | F |
| Dirt Speed | F | B |
| Turf Speed | D | C |
| Distance Speed | B | B |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | F | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | F |
| Early Pace | C | B |
| Mid Pace | F | D |
| Late Pace | D | D |
| Sprint FPS | D | C |
| Route FPS | F | D |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | F | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | D |
| Early Pace | B | A |
| Mid Pace | C | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Big last-race effort (71) — 9 pts above recent average. (2) Early pace significantly above field median (E1: 88 vs field 85). (3) Has won at today's distance (1210 yds) within the last 10 starts — proven ability at this trip. (4) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (5) Carries 5 lbs less than field median (117 lbs vs median 122 lbs). (6) Career-best figure (84) buried in races 4–10 back — 14 pts above race median and 13 pts above recent form — market has forgotten the peak effort. (7) Had documented trouble last race (codes: ['B', 'L', 'T', 'V']) yet still finished 4th — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Repeatedly beaten at this class level (4 of last 5 starts). (2) Trip note from last race: 3w; btwn; evenly. (3) No workout in last 30 days despite 17 days since last race.
Mod1(W): 8 (9/12) Mod2(W): 22 (9/12) Mod3(W): 30 (10/12) Mod1-LS: 53 (9/12) Mod2-LS: 21 (9/12) Mod3-LS: 37 (11/12) Mod4(Form): 1 (10/12) Win Prob: 21.7% Value Score: 6.55 ★ ML: 20.00 (20/1) Overlay %: 3.50 Fair Odds: 13.66 (12/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | F | D |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | B |
| Early Pace | B | A |
| Mid Pace | B | A |
| Late Pace | D | C |
| Finish Pos | B | D |
| Dirt Speed | C | A |
| Turf Speed | D | B |
| Distance Speed | C | B |
| Trainer Effectiveness | D | F |
| Jockey Effectiveness | C | D |
| 3rd Party Ratings | C | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | C |
| Early Pace | D | C |
| Mid Pace | F | C |
| Late Pace | B | C |
| Sprint FPS | C | B |
| Route FPS | D | C |
| Trainer Effectiveness | D | F |
| Jockey Effectiveness | C | D |
| 3rd Party Ratings | C | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | C |
| Early Pace | C | B |
| Mid Pace | B | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Dropping in class today ($7,500 → $5,000). (2) Speed average (76) well above field median (70). (3) Late pace significantly above field median (LP: 80 vs field 74). (4) Has won at today's distance (1210 yds) within the last 10 starts — proven ability at this trip. (5) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (6) Career-best figure (94) buried in races 4–10 back — 24 pts above race median and 20 pts above recent form — market has forgotten the peak effort. (7) Had documented trouble last race (codes: ['D', 'L', 'O', 'T', 'U']) yet still finished 4th — a clean trip today sets up a form reversal. (8) Averages 78.2 speed pts in today's distance/surface configuration vs 65.0 in other configs (8 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Consider there will be likely pace pressure in this race - multiple E types entered. (2) Trip note from last race: Angled out; mild rally. (3) Consistently breaks behind post position (3 of last 5 starts). (4) Consistently runs wide at the first call (3 of last 5 starts). (5) No workout in last 30 days despite 26 days since last race.
Mod1(W): 75 (3/12) Mod2(W): 75 (3/12) Mod3(W): 68 (4/12) Mod1-LS: 70 (4/12) Mod2-LS: 71 (3/12) Mod3-LS: 91 (3/12) Mod4(Form): 87 (3/12) Win Prob: 38% Value Score: 3 ★ ML: 4.50 (7/2) Overlay %: -4.32 Fair Odds: 10.97 (10/1) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | B |
| Early Pace | C | B |
| Mid Pace | B | B |
| Late Pace | A | A |
| Finish Pos | B | D |
| Dirt Speed | A | A |
| Turf Speed | C | B |
| Distance Speed | F | F |
| Trainer Effectiveness | B | C |
| Jockey Effectiveness | C | D |
| 3rd Party Ratings | A | B |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | C |
| Early Pace | B | B |
| Mid Pace | C | B |
| Late Pace | A | B |
| Sprint FPS | A | A |
| Route FPS | B | B |
| Trainer Effectiveness | B | C |
| Jockey Effectiveness | C | D |
| 3rd Party Ratings | A | B |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | B |
| Early Pace | B | B |
| Mid Pace | B | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Big last-race effort (67) — 13 pts above recent average. (2) Early pace significantly above field median (E1: 94 vs field 85). (3) Has won at today's distance (1210 yds) within the last 10 starts — proven ability at this trip. (4) Carries 7 lbs less than field median (115 lbs vs median 122 lbs). (5) Speed improved +17 pts then +12 pts in last 2 starts (38 → 55 → 67) — trainer is progressively building fitness. (6) Career-best figure (84) buried in races 4–10 back — 14 pts above race median and 17 pts above recent form — market has forgotten the peak effort.
⚠ Concerns:(1) Repeatedly beaten at this class level (3 of last 5 starts). (2) Poor recent form - recent speed ratings well below career norm. (3) Consider there will be likely pace pressure in this race - multiple E types entered. (4) Poor record at this track (0 wins from 6 starts). (5) Trip note from last race: Vied inside; tired. (6) Has not won in last 10 starts despite career wins. (7) No workout in last 30 days despite 17 days since last race. (8) Speed figures are highly erratic over last 5 starts (σ = 15.0 pts: [67, 55, 38, 68, 77]) — unpredictable performer.
Mod1(W): 4 (11/12) Mod2(W): 31 (8/12) Mod3(W): 41 (8/12) Mod1-LS: 70 (5/12) Mod2-LS: 29 (8/12) Mod3-LS: 72 (4/12) Mod4(Form): 1 (11/12) Win Prob: 15.1% Value Score: 4.56 ★ ML: 20.00 (20/1) Overlay %: 3.97 Fair Odds: 12.71 (12/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | C |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | F | D |
| Finish Pos | A | C |
| Dirt Speed | C | A |
| Turf Speed | A | B |
| Distance Speed | A | A |
| Trainer Effectiveness | C | D |
| Jockey Effectiveness | F | F |
| 3rd Party Ratings | C | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | F |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | F | F |
| Sprint FPS | A | A |
| Route FPS | B | B |
| Trainer Effectiveness | C | D |
| Jockey Effectiveness | F | F |
| 3rd Party Ratings | C | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | C |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 32-day layoff with a recent workout. (2) Closer/presser in a race with pace pressure — ideal race setup for late runners. (3) Outstanding wet-track record: 1W from 4 starts (25%) — thrives when the going is off.
⚠ Concerns:(1) Has not raced in 32 days. (2) Repeatedly beaten at this class level (5 of last 5 starts). (3) Poor record at this distance (0 wins from 7 recent starts). (4) Trip note from last race: Gave way readily. (5) Consistently breaks behind post position (4 of last 5 starts). (6) Consistently runs wide at the first call (4 of last 5 starts). (7) Post 7 in a 13-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (8) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 0 Mod2(W): 0 Mod3(W): 0 Mod1-LS: 0 Mod2-LS: 0 Mod3-LS: 0 Mod4(Form): 0 (12/12) Win Prob: 13.5% Value Score: 4.08 ★ ML: 20.00 (20/1) Overlay %: 3.61 Fair Odds: 13.43 (12/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | D | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | C |
| Early Pace | F | D |
| Mid Pace | F | C |
| Late Pace | C | C |
| Finish Pos | F | F |
| Dirt Speed | D | B |
| Turf Speed | C | B |
| Distance Speed | C | B |
| Trainer Effectiveness | D | F |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | F | D |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | D |
| Early Pace | F | C |
| Mid Pace | D | C |
| Late Pace | C | C |
| Sprint FPS | F | D |
| Route FPS | F | D |
| Trainer Effectiveness | D | F |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | F | D |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | D |
| Early Pace | F | C |
| Mid Pace | F | C |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Has won at today's distance (1210 yds) within the last 10 starts — proven ability at this trip. (2) Outstanding wet-track record: 2W from 7 starts (29%) — thrives when the going is off. (3) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo. (4) Last race E1 pace (93.0) was 8.1 pts above personal avg (84.9) and horse still finished 8th — pace collapse victim; expect bounce if today's fractions are softer. (5) Averages 65.0 speed pts in today's distance/surface configuration vs 57.2 in other configs (6 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Has not raced in 107 days. (2) Repeatedly beaten at this class level (5 of last 5 starts). (3) Consider there will be likely pace pressure in this race - multiple E types entered. (4) Speed average (62) well below field median (70). (5) Moving from a route to a sprint today. (6) Trip note from last race: Inside duel; gave way. (7) Consistently breaks behind post position (3 of last 5 starts). (8) Cold trainer - low ITM rate (7%). (9) Outside post (8) in a large field of 13 horses. (10) Post 8 in a 13-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (11) Speed figures are highly erratic over last 5 starts (σ = 9.1 pts: [48, 63, 55, 65, 44]) — unpredictable performer.
Mod1(W): 1 (12/12) Mod2(W): 3 (12/12) Mod3(W): 8 (12/12) Mod1-LS: 21 (12/12) Mod2-LS: 3 (12/12) Mod3-LS: 38 (10/12) Mod4(Form): 0 Win Prob: 16.6% Value Score: 5.01 ★ ML: 20.00 (20/1) Overlay %: 3.37 Fair Odds: 13.94 (12/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | C | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | F | D |
| Early Pace | C | B |
| Mid Pace | D | B |
| Late Pace | F | D |
| Finish Pos | F | F |
| Dirt Speed | C | A |
| Turf Speed | B | B |
| Distance Speed | D | C |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | F | F |
| 3rd Party Ratings | D | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | F |
| Early Pace | C | C |
| Mid Pace | D | C |
| Late Pace | F | D |
| Sprint FPS | D | D |
| Route FPS | D | C |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | F | F |
| 3rd Party Ratings | D | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | F | D |
| Early Pace | D | B |
| Mid Pace | D | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Speed average (79) well above field median (70). (2) Hot trainer - high ITM rate (43%). (3) Hot jockey — high ITM rate (46%). (4) In the money in last 3 consecutive starts. (5) Track specialist — 4 wins from 16 starts here (25%). (6) Early pace significantly above field median (E1: 91 vs field 85). (7) Late pace significantly above field median (LP: 77 vs field 74). (8) Fourth race back from a 64-day layoff — often the peak fitness race. (9) Returning from 32-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (10) Had documented trouble last race (codes: ['D', 'L']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 32 days. (2) Was claimed from its most recent race - new connections. (3) Consider there will be likely pace pressure in this race - multiple E types entered. (4) Poor record at this distance (0 wins from 10 recent starts). (5) Trip note from last race: Clear; wdnd; weakened. (6) Outside post (9) in a large field of 13 horses. (7) Has not won in last 10 starts despite career wins. (8) No workout in last 30 days despite 32 days since last race. (9) Post 9 in a 13-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (10) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 78 (2/12) Mod2(W): 86 (2/12) Mod3(W): 90 (2/12) Mod1-LS: 89 (2/12) Mod2-LS: 83 (2/12) Mod3-LS: 66 (5/12) Mod4(Form): 94 (2/12) Win Prob: 47.9% Value Score: 3.44 ★ ML: 4.00 (3/1) Overlay %: -4.78 Fair Odds: 9.91 (9/1) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | A |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | B | B |
| Finish Pos | A | C |
| Dirt Speed | A | A |
| Turf Speed | F | D |
| Distance Speed | B | B |
| Trainer Effectiveness | A | B |
| Jockey Effectiveness | A | B |
| 3rd Party Ratings | A | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | B |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | B | C |
| Sprint FPS | B | A |
| Route FPS | A | B |
| Trainer Effectiveness | A | B |
| Jockey Effectiveness | A | B |
| 3rd Party Ratings | A | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | B |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Hot trainer - high ITM rate (42%). (2) Hot jockey — high ITM rate (43%). (3) Outstanding wet-track record: 2W from 5 starts (40%) — thrives when the going is off. (4) Career-best figure (81) buried in races 4–10 back — 11 pts above race median and 5 pts above recent form — market has forgotten the peak effort.
⚠ Concerns:(1) Finish positions worsening over last 4 starts. (2) Moving from a route to a sprint today. (3) Poor record at this distance (0 wins from 7 recent starts). (4) Trip note from last race: Wide; gave way. (5) Consistently breaks behind post position (3 of last 5 starts). (6) Outside post (10) in a large field of 13 horses. (7) No workout in last 30 days despite 18 days since last race. (8) Post 10 in a 13-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (9) Speed figures are highly erratic over last 5 starts (σ = 9.1 pts: [57, 74, 76, 81, 74]) — unpredictable performer. (10) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 26 (6/12) Mod2(W): 38 (6/12) Mod3(W): 45 (6/12) Mod1-LS: 75 (3/12) Mod2-LS: 38 (6/12) Mod3-LS: 100 (1/12) Mod4(Form): 43 (6/12) Win Prob: 28% Value Score: 4.41 ★ ML: 10.00 (9/1) Overlay %: 1.48 Fair Odds: 11.80 (10/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | B | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | C |
| Early Pace | D | C |
| Mid Pace | D | B |
| Late Pace | B | B |
| Finish Pos | D | F |
| Dirt Speed | A | A |
| Turf Speed | A | B |
| Distance Speed | F | F |
| Trainer Effectiveness | B | C |
| Jockey Effectiveness | A | B |
| 3rd Party Ratings | B | B |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | C |
| Early Pace | C | C |
| Mid Pace | C | B |
| Late Pace | D | D |
| Sprint FPS | C | B |
| Route FPS | C | B |
| Trainer Effectiveness | B | C |
| Jockey Effectiveness | A | B |
| 3rd Party Ratings | B | B |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | B | C |
| Early Pace | D | C |
| Mid Pace | D | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Hot trainer - high ITM rate (42%). (2) Has won at today's distance (1210 yds) within the last 10 starts — proven ability at this trip. (3) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo.
⚠ Concerns:(1) Repeatedly beaten at this class level (3 of last 5 starts). (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Trip note from last race: Hit gate; off slowly. (4) Outside post (11) in a large field of 13 horses. (5) No workout in last 30 days despite 17 days since last race. (6) Post 11 in a 13-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (7) Speed figures are highly erratic over last 5 starts (σ = 14.4 pts: [47, 71, 83, 78, 61]) — unpredictable performer.
Mod1(W): 25 (7/12) Mod2(W): 35 (7/12) Mod3(W): 44 (7/12) Mod1-LS: 64 (6/12) Mod2-LS: 33 (7/12) Mod3-LS: 64 (6/12) Mod4(Form): 42 (7/12) Win Prob: 31.3% Value Score: 4.94 ★ ML: 10.00 (9/1) Overlay %: 1.23 Fair Odds: 12.21 (12/1) O/U: Fair
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | C | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | C |
| Early Pace | D | B |
| Mid Pace | C | B |
| Late Pace | C | C |
| Finish Pos | D | F |
| Dirt Speed | F | B |
| Turf Speed | B | B |
| Distance Speed | D | C |
| Trainer Effectiveness | B | C |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | D | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | C |
| Early Pace | B | B |
| Mid Pace | B | B |
| Late Pace | C | C |
| Sprint FPS | B | B |
| Route FPS | B | B |
| Trainer Effectiveness | B | C |
| Jockey Effectiveness | D | D |
| 3rd Party Ratings | D | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | C |
| Early Pace | C | B |
| Mid Pace | C | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 31-day layoff with a recent workout. (2) Late pace significantly above field median (LP: 77 vs field 74). (3) Closer/presser in a race with pace pressure — ideal race setup for late runners. (4) Has won at PRX on dirt in the last 10 starts — proven at today's exact track/surface combo.
⚠ Concerns:(1) Has not raced in 31 days. (2) Repeatedly beaten at this class level (3 of last 5 starts). (3) Poor record at this distance (0 wins from 7 recent starts). (4) Trip note from last race: Sluggish; no response. (5) Consistently breaks behind post position (3 of last 5 starts). (6) Consistently runs wide at the first call (3 of last 5 starts). (7) Outside post (12) in a large field of 13 horses. (8) Post 12 in a 13-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (9) Speed figures are highly erratic over last 5 starts (σ = 13.8 pts: [51, 48, 79, 70, 73]) — unpredictable performer.
Mod1(W): 6 (10/12) Mod2(W): 17 (10/12) Mod3(W): 27 (11/12) Mod1-LS: 57 (8/12) Mod2-LS: 19 (11/12) Mod3-LS: 49 (8/12) Mod4(Form): 15 (9/12) Win Prob: 36.3% Value Score: 8.33 ★ ML: 15.00 (15/1) Overlay %: 2.24 Fair Odds: 14.16 (12/1) O/U: Overlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | F | C |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | C |
| Early Pace | F | D |
| Mid Pace | D | C |
| Late Pace | B | B |
| Finish Pos | C | D |
| Dirt Speed | D | A |
| Turf Speed | D | C |
| Distance Speed | B | B |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | B | C |
| 3rd Party Ratings | D | C |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | D | D |
| Early Pace | F | C |
| Mid Pace | D | C |
| Late Pace | C | D |
| Sprint FPS | F | D |
| Route FPS | D | D |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | B | C |
| 3rd Party Ratings | D | C |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | C | C |
| Early Pace | F | C |
| Mid Pace | D | B |
| Late Pace | C | C |
Chart Guide (2.0.35)
- Bubbles
- Color = surface: green (turf), brown (dirt), blue (synthetic)
- Top number = finishing position; bottom number in parentheses = starting post position
- Height above line = beaten lengths — closer means a smaller margin
- Border = track conditions: green (FST/GD/FM), yellow (WF/SL/YLD), red (SY/MY/FRZ/SFT/HVY)
- Connecting Line
- Solid = good conditions; dashed = bad conditions
- Line Symbol
- ▲ Triangle = sprint (7f or less); ● Circle = route (more than 7f)
- Days Between Races
- Small number above each bubble (e.g. 19d) = days since the previous race — helps spot freshness, layoffs, and tight scheduling.
- Shaded Band (Bollinger)
- Highlights volatility — a wider band means more variation in recent performance
- Performance Trend
- Straight line showing the overall performance direction — angled up = improving, angled down = declining
- Dashed Reference Line
- AI Opponent = AI analysis class-level par for the race
✓ Positives:(1) Returning from 31-day layoff with a recent workout. (2) Speed average (81) well above field median (70). (3) Hot trainer - high ITM rate (60%). (4) Strong trainer/jockey combo - 13 wins from 42 starts (31%). (5) Hot jockey — high ITM rate (52%). (6) Early pace significantly above field median (E1: 93 vs field 85). (7) Late pace significantly above field median (LP: 78 vs field 74). (8) Has won at today's distance (1210 yds) within the last 10 starts — proven ability at this trip. (9) Returning from 31-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (10) Trainer 'NESS JAMIE' has 2 horses in today's card all showing last-race improvement — barn appears sharp right now. (11) Career-best figure (90) buried in races 4–10 back — 20 pts above race median and 5 pts above recent form — market has forgotten the peak effort. (12) Had documented trouble last race (codes: ['D', 'S', 'U']) yet still finished 1st — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 31 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Trip note from last race: Prsd ins; cued3w;up1/8. (4) Outside post (13) in a large field of 13 horses. (5) Dropping in class in consecutive starts ($25,000 → $7,500 → $4,000). (6) Post 13 in a 13-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (7) Speed figures are highly erratic over last 5 starts (σ = 8.7 pts: [83, 85, 67, 90, 84]) — unpredictable performer.
Mod1(W): 100 (1/12) Mod2(W): 100 (1/12) Mod3(W): 100 (1/12) Mod1-LS: 100 (1/12) Mod2-LS: 100 (1/12) Mod3-LS: 95 (2/12) Mod4(Form): 100 (1/12) Win Prob: 43.8% Value Score: 2.83 ★ ML: 3.50 (5/2) Overlay %: -6.19 Fair Odds: 9.75 (9/1) O/U: Underlay
Score Definitions
- Mod1(W)
- Winner Model 1 score (0–100) — AI composite rating among field contenders (higher = stronger). The number in parentheses (e.g. 1/9) shows this horse’s rank out of the field size.
- Mod2(W)
- Winner Model 2 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod3(W)
- Winner Model 3 score (0–100) — AI rating among field contenders (higher = stronger). The number in parentheses shows rank within the field.
- Mod1-LS
- Longshot Model 1 score (0–100) — AI model trained to surface high-value longshots. Higher = stronger longshot profile. Rank in parentheses shows position within the field.
- Mod2-LS
- Longshot Model 2 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod3-LS
- Longshot Model 3 score (0–100) — AI longshot model. Higher = stronger longshot profile.
- Mod4(Form)
- Form Model score (0–100) — AI sequence model trained on recent form patterns to capture momentum and trajectory. Higher = stronger recent form profile. Rank in parentheses shows position within the field.
- Win Prob
- LightGBM estimated win probability expressed as a percentage. This is a raw model output, not normalized to sum to 100% across the field — use it for comparison rather than as an absolute probability.
- Value Score
- Win Prob divided by the market-implied probability (derived from morning line). Values above 1.0 mean the model sees more win chance than the odds imply — a ★ star appears when Value Score ≥ 1.3, indicating a 30%+ model edge over the market.
- ML
- Morning line odds set by the track handicapper before wagering opens
- Overlay %
- How much the fair odds exceed the morning line, expressed as a percentage — positive values indicate value
- Fair Odds
- Model-derived fair-value odds based on estimated win probability
- O/U
- Overlay or Underlay — whether the horse offers value (O) or is overbet (U) relative to fair odds
Lane Bias Guide
- Bar Direction
- Bars above the line = more favorable lane • Bars below = less favorable, relative to the average at this track.
- Color
- Green = above-average advantage • Yellow = near-average • Red = below-average • Blue = this horse’s lane.
- Bias Score
- Derived from weighted average finishing positions across historical races at this track. Shown in the tooltip on hover. To use the bias score, calculate your handicap for the horse (e.g. finish position), then add (detrimental bias) or subtract (favorable bias) the bias score.
- Races
- Number of historical races used to compute each lane’s bias score.
Race Pace Bias Guide
- Bar Height & Direction
- Positive (green) = pace favors this horse • Negative (red) = pace works against this horse • Near-zero (amber) = neutral.
- Race Shape
- Projected race shape based on running styles of all horses (e.g. EE = two early horses, EP = one early presser).
- Pace Category
- FAST = contested early pace • LONE EARLY = one speed horse controlling pace • HONEST = moderate early pressure • SLOW = closers’ race.
- Flag (★)
- A star above the bar means this horse’s pace bias figure is ≥ 1.5 — a meaningful pace advantage or disadvantage.
Total Pace Guide
- Bar Segments
- Green = Early Pace (E1) • Amber = Mid Pace (E2) • Red = Late Pace (LP)
- Bar Height
- Total height = sum of E1 + E2 + LP average pace figures. Taller bars indicate a faster-paced horse overall.
- Grades & Rankings
- Hover to see each horse’s letter grade and ranking vs. other horses in this race (e.g. 2/9 = 2nd best of 9).
- Border
- Thicker border = this horse’s post position.
Performance vs. Peers Guide
- Bars (per post)
- Blue = avg career performance • Amber = avg last 3 races • Green = last race (improved vs. avg) • Red = last race (declined vs. avg)
- Trend Line
- Angled line above the bars: rising = improving form • falling = declining form.
- Horizontal Line
- Field average — the mean career performance of all horses in this race.
- Color Circles
- Standard post-position colors below each lane — same as the Total Pace chart.
- Border
- Thicker border = this horse’s post position.
Figure Comparison
- Rating
- The three Pick Pony algorithm ratings (Algo 1, Algo 2, Algo 3) that make up the overall PP AI Rating — higher is a stronger contender rating.
- Speed
- Career average speed, recent 3-race average, and last-race speed figure — spot horses in improving or declining form.
- Pace
- Average Early (E1), Mid (E2), and Stretch (LP) pace figures — reveals pace-setters vs. closers vs. all-the-way types.
- This horse
- The horse whose stats card is open is highlighted with a darker column background.
Winning Profiles
- Axes
- X: Win % from last 10 starts — Y: In-the-money % (top-3 finishes) from last 10 starts.
- Quadrants
- Consistent Winners (top-right): high win & ITM — reliable performers.
Place Threats (top-left): boards often but doesn’t win often — good exacta/trifecta angles.
Streaky (bottom-right): wins occasionally, misses the board often — all-or-nothing.
Developing (bottom-left): still finding form — longshot territory. - Reference Lines
- Dashed lines mark field averages. Dots to the right win more; dots higher board more.
- This horse
- Highlighted with a gold border and larger dot.
AI Model Comparison
- Winner Models (green)
- Mod1(W), Mod2(W), and Mod3(W) trained to predict race winners. Higher score = stronger contender.
- Longshot Models (red)
- Mod1-LS, Mod2-LS, and Mod3-LS trained to find high-value longshots. Higher score = stronger longshot candidate.
- Form Model (blue)
- Mod4 sequence model trained on recent form patterns. Higher score = stronger recent form profile.
- This horse
- Highlighted with a darker column background.
Race Pace Simulation Guide
- Slider
- Drag left→right to advance from gate to finish. Drag all the way back to reset the race.
- Predicted Finish Order
- Factors in contested pace burn, each horse’s effort curve (peaked-early vs. peaked-late), and wide trip cost from outside posts. Updated live when Track Bias changes.
- Pace Scenario
- Lone Speed: single E horse likely rates and holds. Contested: two E horses burn each other — closers benefit. Hot Pace: speed meltdown, deep closers thrive. Soft: no early speed, moderate fractions throughout.
- Track Bias
- Slider below canvas. −2 = strong closer/wet bias; +2 = strong speed/rail bias. Recomputes the predicted finish order.
- Boxed Indicator
- Dashed orange ring = horse is surrounded (rival ahead, rival behind, wall outside). In a real race this horse must find a clear path to run.
- Running Styles
- E/EE = early speed (rushes to rail). P = presser (stalks the pace). S = stalker. SS = slow starter / closer.
| Stat | vs. Current Card | vs. All Horses |
|---|---|---|
| Averages
Career-average metrics across all AI race analysis. Performance and pace averages reflect estimated historical performance; trainer and jockey grades score in-the-money percentages. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Pick Pony AI Rating | A | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | A |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | A | B |
| Finish Pos | A | B |
| Dirt Speed | C | A |
| Turf Speed | B | B |
| Distance Speed | A | A |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | A |
| Recent
Performance analysis from the horse's recent races, weighted to reflect current form. Sprint and Route FPS (Foot Per Second) measure pace efficiency over the horse's recent sprints and routes respectively. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | B |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | A | B |
| Sprint FPS | A | A |
| Route FPS | A | A |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | A |
| 3rd Party Ratings | A | A |
| Predictions
AI-generated projections for the upcoming race, derived from prior AI analysis for speed and pace trends, surface and distance suitability, and current conditions. Grading scale: A = elite • B = above average • C = average • D = below average • F = poor • — = no data |
||
| Speed | A | A |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | C | C |
TL;DR
Toggle
Get more in-depth analysis, expert picks, handicapper reports, AI picks, handicapping tools, in-article data tooltips, NO ADVERTISEMENTS, and other membership perks with a Pick Pony subscription!
The Pick Pony Handicapper's Report is published daily and provides analysis of all races on the card. A Pick Pony analyst prepares the report, so selections may differ from the Pick Pony Expert Picks, which are based on the consensus of all Pick Pony analysts.
Race Day Overview — Parx Racing, Saturday, May 2, 2026
Parx Racing kicks off its Saturday card with a 13-race program beginning at 12:40 PM ET, featuring a mix of maiden claimers, claimers, and optional claimers ranging in purse value from $18,000 in the cheap maiden sprint to $52,000 in the featured Route 8 event. The card skews heavily toward the claiming ranks, with several older horse races offering legitimate class questions and pace setups that reward sharp handicapping. Saturday afternoon cards at Parx routinely draw competitive fields from the mid-Atlantic circuit, and this program is no exception — trainer barns from the full spectrum of the Parx colony are represented, from the deep operations of Michael Pino and Jamie Ness to the smaller outfits grinding out wins at the bottom of the claiming ladder.
Of particular note is Race 7, the optional claimer for $75,000 non-winners of two lifetime, which is the consensus best bet target on the card and the race that carries the most significant handicapping angles. Race 8 is the highest-purse event of the afternoon at $52,000 over a route distance and figures to generate the most exotic play.
The full card is contested on the main dirt track. No turf races are carded today.
Weather and Track Conditions — May 2, 2026
The Philadelphia region is forecast to see mild spring conditions on Saturday, with temperatures climbing into the upper 50s to low 60s Fahrenheit by post time for the first race. Partly cloudy skies are expected throughout the afternoon with minimal chance of precipitation. Overnight moisture from the prior week's unsettled pattern may leave the track slightly sealed at the surface, though conditions are expected to trend toward fast or good by mid-afternoon. Any lingering dampness would favor horses with good tactical speed that can secure a clean trip without getting too far back and dealing with the kickback.
Bettors should monitor Equibase track condition updates leading into the first post, as a sealed or good track at Parx can play quite differently from a genuinely fast surface. Historically, a sealed Parx main track tends to favor horses with early foot who can get to the rail and take advantage of a firmer inside path.
Track Bias and Post Position Analysis
Parx Racing's main dirt track is a one-mile oval that historically shows a pronounced speed bias, particularly at sprint distances. Horses that establish a position on or near the lead through the early fractions consistently outperform closers here, especially when the track is sealed or fast. The track's tight turns and relatively short stretch run make it difficult for deep closers to overcome a deficit if the pace is only moderately contested.
At sprint distances — particularly the 1320-foot (one-turn mile equivalent, though Parx uses furlongs, so 1320 feet represents approximately six furlongs) and 1210-foot configurations — inside post positions have historically offered a meaningful advantage, provided the horse can break alertly and secure a forward position early. Outside posts at sprint distances require a jockey who is willing to angle the horse to the inside or settle off the pace, which at Parx generally constitutes a losing strategy unless the pace is blistering.
At route distances, the inside post advantage is somewhat neutralized by the longer run to the first turn, and horses breaking from posts 4 through 7 tend to have optimal trip flexibility. Post 1 at route distances can be a trap if the horse is a confirmed stalker or closer, as rail trips in traffic can leave riders boxed with no room to maneuver.
Given a potentially sealed surface early in the day, speed horses on the inside from posts 1 through 3 should receive added attention in today's sprint races. The afternoon may loosen up as racing progresses and traffic grinds the moisture out of the surface, potentially giving slightly more play to off-the-pace runners in the later races.
RACE 1 — Post (12:40)/11:40/10:40/9:40 — 1320f | D | M | Md 10000 | BUN | Purse $19,000
This is a maiden claiming sprint at the lowest level on today's card, $10,000 maiden claimers going six furlongs on the dirt. Fields like this at the bottom of the maiden claiming ladder at Parx are often filled with horses that have shown some ability but consistently fail to break their maiden, along with first-time starters whose connections have a modest appraisal of their talent. With a purse of $19,000 and a tag this low, most of these horses are racing to earn and to begin their claiming career.
Race 1
Pace Analysis
With eight runners entered at six furlongs, the pace question centers on how many horses want to be on or near the lead early. Mi Hermano (POST 6), the morning line favorite at 2-1 trained by Michael Pino, figures to be prominent early given the Pino barn's tendency to position horses well off the break. Warheaded (POST 3) at 4-1 and Gentleman Don (POST 2) at 3-1 also project as potential speed types. If multiple horses contest the lead aggressively through the first quarter, it could set up a pace meltdown that benefits a closer, though closers at Parx at this level rarely benefit enough from pace collapse to overcome the bias. More likely is a moderate pace scenario where the horse that settles into a good tactical position on or near the lead controls the race.
Key Contenders
Mi Hermano (POST 6) draws the attention of most handicappers as the morning line favorite at 2-1. Trained by Michael Pino, one of the more active and successful conditioners at Parx, this runner has the class of barn backing and jockey Mychel Sanchez, who ranks among the leading riders at the meet. Pino horses at this level typically arrive fit and ready, and Sanchez's ability to get horses into position early in sprint races is a significant asset at Parx. The 2-1 morning line is fairly short for a maiden claimer, which suggests either strong workout activity or recent competitive form that screams for a maiden tag win.
Gentleman Don (POST 2) at 3-1 trained by Bobbi Anne Hawthorne with Kendry Rivera up is another leading contender. Post 2 is ideal for a six-furlong sprint at Parx, as it allows the jockey to secure early position without having to use excessive energy. The 3-1 morning line indicates the morning line maker sees this as a genuine contender to the favorite, and Rivera is a capable rider who knows how to maximize trips from good posts.
Secondary Choices
Warheaded (POST 3) at 4-1 trained by Jacinto Solis with Joezer Rangel aboard is the third choice in the morning line and warrants consideration. Post 3 is another favorable gate position for a sprint, and the 4-1 price offers decent value if this runner shows early speed. Solis is a smaller outfit at Parx, which means less public attention and potentially better mutual odds if this horse hits the board.
Ten Plus Ten (POST 1) at 6-1 trained by Gustavo Chacon with Jean Aguilar gets the rail, which in a sprint at Parx can be a true advantage if the rider breaks alertly and gets to the rail position before the first turn. At 6-1 on the morning line, this is live value if the horse breaks well.
Longshots
Tap The Devil (POST 7) at 8-1 and Craigh Na Dun (POST 8) at 8-1 are the primary longshots. TAP THE DEVIL is trained by Melecio Saldana Guerrero, a smaller barn, with A. Castillo up. From the seven post in a six-furlong sprint, this horse will need to break sharply to avoid wide trips. CRAIGH NA DUN trained by Alan Bedard with Adam Bowman is also a longshot at 8-1. Bedard occasionally sends sharp horses at this level that sneak up on the public, and Bowman is a competent rider. At double digits or near, this is a horse to watch in the paddock for signs of readiness.
Chilling Time (POST 4) at 15-1 and Rogue Prince (POST 5) at 15-1 round out the field. CHILLING TIME trained by Herold Whylie with Silvestre Gonzalez has very little form to recommend at this level. ROGUE PRINCE trained by J. Tyler Servis, though Servis typically has better horses than this level, at 15-1 this remains a play-against unless there is a significant equipment or class drop angle working in the horse's favor.
Betting Strategy
The race sets up as a likely two-horse battle between Mi Hermano (POST 6) and Gentleman Don (POST 2), with Warheaded (POST 3) as the probable third. For win betting, Mi Hermano (POST 6) at 2-1 is fairly short but represents the strongest overall package of trainer, jockey, and post position. An exacta box of Mi Hermano (POST 6) and Gentleman Don (POST 2) with Warheaded (POST 3) underneath represents the best ticket construction. At this level, the pace can be chaotic, so keeping Ten Plus Ten (POST 1) alive in trifectas is a low-cost addition that could pay well if the rail horse runs big.
Selections
Win: Mi Hermano (POST 6) Place: Gentleman Don (POST 2) Show: Warheaded (POST 3)
RACE 2 — Post (1:07)/12:07/11:07/10:07 — 1320f | D | C | Clm 7500n3l | BUM | Purse $21,000
A six-furlong claiming sprint for fillies and mares that have not won three races lifetime. The $7,500 claiming price puts this at the lower end of the claiming ladder but a step above the maidens. With seven runners entered, the field is manageable and the pace picture is relatively clear.
Race 2
Pace Analysis
Mila Rose (POST 3) and Neighbelline (POST 4) are co-favorites at 2-1 and are the two main focal points for pace analysis. At six furlongs with a small field, if one of the two favorites controls the early fractions uncontested, she becomes very difficult to beat. Twist Her (POST 1) from the rail with Kendry Rivera could also be involved early and will look to take advantage of the inside post. A genuine speed duel between Mila Rose (POST 3) and Twist Her (POST 1) could open the door for Neighbelline (POST 4) to stalk and pounce.
Key Contenders
Mila Rose (POST 3) at 2-1 trained by Ruperto Perez with Francisco Martinez is one of two co-morning-line favorites. Post 3 is ideal for a six-furlong sprint, and Martinez has been among the busier riders at the meet. At this level, trainer Perez knows how to place horses at their optimal spot, and this mare appears to be pointing here at her best distance.
Neighbelline (POST 4) at 2-1 trained by Marya Montoya with Mychel Sanchez is the other co-favorite and arguably the stronger play given the Sanchez booking. Montoya is a capable Parx conditioner, and the Sanchez connection gives this horse a significant tactical advantage. From post 4, Sanchez will have a clean view of the early pace and can dictate his trip accordingly.
Secondary Choices
Twist Her (POST 1) at 4-1 trained by Michael Moore with Kendry Rivera holds down the rail and could be a very interesting play if she shows early speed. Moore is one of the more reliable conditioners at Parx and TWIST HER at 4-1 represents decent value if she can use her post position advantageously. Rivera from the rail will likely take back early or try to save ground into the first turn.
Girl Dynamite (POST 2) at 6-1 trained by Melecio Saldana Guerrero with Noel Herman is a secondary option. Post 2 is a solid post for sprints, and at 6-1, this mare offers some value in exotics if she shows improvement.
Longshots
She Can Scat (POST 5) at 10-1 trained by Howard Brown Jr. with Luis Rivera is a double-digit price that could easily hit the board if the pace collapses. Arrivedercci (POST 6) at 12-1 trained by John Volpe with Adam Bowman is another longer price. Volpe is a smaller outfit at Parx and this horse at double digits is primarily of exotic interest only. Brooklyn Heights (POST 7) at 15-1 trained by Uriah St. Lewis with Patrick Henry Jr. is the longest price in the field. St. Lewis has horses at this level of the barn and occasionally springs surprises, but 15-1 on the morning line is likely fair or generous for a reason.
Betting Strategy
The race hinges on whether Mila Rose (POST 3) or Neighbelline (POST 4) controls the pace. An exacta with both horses covering each other — Mila Rose (POST 3) over Neighbelline (POST 4) and Neighbelline (POST 4) over Mila Rose (POST 3) — is a sensible approach. Adding Twist Her (POST 1) as a second-place finisher in a trifecta box with the two co-favorites is an inexpensive way to play this race. At 4-1, Twist Her (POST 1) as a place or show bet also has appeal.
Selections
Win: Neighbelline (POST 4) Place: Mila Rose (POST 3) Show: Twist Her (POST 1)
RACE 3 — Post (1:34)/12:34/11:34/10:34 — 1540f | D | C | Clm 12500n3l | BUM | Purse $23,000
A seven-furlong claiming event for fillies and mares that have not won three lifetime at the $12,500 level. Seven runners make this another manageable field, and the slightly longer distance compared to the earlier sprints adds a layer of stamina consideration. At seven furlongs, a horse that can rate just off the pace and close with authority has a better chance than it would at six furlongs, though the Parx speed bias still applies.
Race 3
Pace Analysis
Leilauni Sue (POST 1) is the morning line favorite at 2-1 and from the rail at seven furlongs, she is in a terrific position to control the pace or sit right behind the leader. Lost Love (POST 7) at 3-1 is the second choice and figures to be a stalker or closer. If Leilauni Sue (POST 1) can dictate a comfortable pace, she becomes very difficult to beat from the rail. However, if Melody's Kiss (POST 3) or Joyful Joyce (POST 4) applies pressure early, the pace could set up for a closer like Lost Love (POST 7).
Key Contenders
Leilauni Sue (POST 1) at 2-1 trained by Michael Moore with Andy Hernandez is the clear favorite and the horse to beat. Moore with Hernandez is a competent combination at Parx, and the rail post at seven furlongs gives Leilauni Sue (POST 1) every opportunity to control the race on her own terms. At 2-1, the price is tight, but in a small field at this level, the favorite often delivers.
Lost Love (POST 7) at 3-1 trained by Tim Shaw with Abner Adorno is the main danger. Shaw has done solid work at Parx and Lost Love (POST 7) from the outside post will likely come off the pace. Adorno is a capable finisher's rider who can navigate from the outside if the pace sets up.
Secondary Choices
Melody's Kiss (POST 3) at 4-1 trained by Junior Nicholson with Silvestre Gonzalez is the third choice in the morning line. Post 3 at seven furlongs is workable, and at 4-1, this mare offers some each-way value. Joyful Joyce (POST 4) at 5-1 trained by J. Guadalupe Guerrero with Francisco Martinez is another live contender. Martinez is an active rider at the meet, and Guerrero places horses well at this level.
Leretha (POST 5) at 5-1 trained by Kathlee Crook-Demasi with Mychel Sanchez is a strong play at the price. The Sanchez booking is significant here — any time Sanchez takes a ride at 5-1 in a claiming race, that is a horse worth serious consideration. Crook-Demasi is a capable conditioner who does not waste the top jock unless the horse has a real shot.
Longshots
West Side Diva (POST 2) at 6-1 trained by Jose Gonzalez-Milian with A. Castillo is the longest priced horse in the field with some realistic chance. Post 2 is favorable, and at 6-1, there is some value if this mare has improved. Flaming Eyes (POST 6) at 10-1 trained by Uriah St. Lewis with Ajhari Williams is a significant longshot. St. Lewis occasionally sends a sharp horse at a price, but 10-1 here suggests limited recent form.
Betting Strategy
Leilauni Sue (POST 1) is the controlling horse, but at 2-1 in a seven-horse field, the win price is low enough that exactas offer better value. A key of Leilauni Sue (POST 1) on top with Leretha (POST 5) and Lost Love (POST 7) underneath is the recommended trifecta structure. Leretha (POST 5) at 5-1 with the Sanchez booking is the best value bet in the race for straight wagering.
Selections
Win: Leilauni Sue (POST 1) Place: Leretha (POST 5) Show: Lost Love (POST 7)
RACE 4 — Post (2:01)/1:01/12:01/11:01 — 1320f | D | M | Md 15000 | BON | Purse $19,000
A six-furlong maiden claimer at the $15,000 level for colts and geldings. Eight runners make this a full sprint field. The step up from the $10,000 maiden field in Race 1 means slightly better horses but the dynamics at Parx remain similar — speed is rewarded and front runners with good posts are the primary targets.
Race 4
Pace Analysis
Cap'n Cats (POST 6) is the morning line favorite at 2-1 and trained by Josue Arce with Melvis Gonzalez. Filled With Desire (POST 4) at 3-1 trained by Michael Pino with Mychel Sanchez is the second choice. This race could see genuine early pressure if both horses want to lead, which would set up something from off the pace. The Fridge (POST 8) at 4-1 is the third choice and figures to come off the pace. If Cap'n Cats (POST 6) and Filled With Desire (POST 4) duel up front, The Fridge (POST 8) closing from the outside could be the beneficiary.
Key Contenders
Filled With Desire (POST 4) at 3-1 trained by Michael Pino with Mychel Sanchez is the horse to beat. The Pino and Sanchez combination is the most powerful at Parx and at 3-1, this is the type of entry that covers the win bet. Post 4 in a six-furlong sprint is workable and Sanchez will have the tactical flexibility to either press or rate depending on how the race develops.
Cap'n Cats (POST 6) at 2-1 trained by Josue Arce with Melvis Gonzalez is the favorite on the morning line and deserves respect. Arce is a smaller barn that periodically springs sharp horses at prices, but at 2-1, the betting public is clearly informed. Gonzalez is an underrated rider at the meet.
Secondary Choices
The Fridge (POST 8) at 4-1 trained by Michael Pino with Noel Herman is a second Pino entry in this race and a legitimate threat. At 4-1 from the outside post, The Fridge (POST 8) will need a pace to run into, but if the early fractions are honest between the two morning line choices, this horse closing from off the pace with a clear trip outside could easily get up for a piece. Two Pino horses in the same race adds complexity — Sanchez and Herman are both experienced enough to execute their intended trips.
Its All Gravy (POST 2) at 6-1 trained by Philip Aristone with A. Castillo is a secondary choice worth including in exotics. Aristone is a solid mid-level trainer at Parx and at 6-1, there is some overlay potential. Festivities (POST 5) at 6-1 trained by Aristone as well with Silvestre Gonzalez represents the trainer's second entry. With two Aristone horses in the race alongside two Pino horses, the barn dynamics could be interesting.
Longshots
Supernova Dream (POST 7) at 6-1 trained by Louis Linder Jr. with Francisco Martinez is another 6-1 horse that could attract some morning line movement. Global Winner (POST 3) at 15-1 trained by Uriah St. Lewis with Kendry Rivera is a substantial price. In The Cloud (POST 1) at 12-1 trained by Alan Bedard with Luis Ocasio rounds out the field from the rail at a long price.
Betting Strategy
With four horses connected to two of the meet's best barns — Pino and Aristone — this race warrants careful study of the wagering pools as they develop. Filled With Desire (POST 4) at 3-1 is the primary bet, with a win/exacta structure putting Filled With Desire (POST 4) on top over Cap'n Cats (POST 6) and The Fridge (POST 8). If The Fridge (POST 8) drifts above 5-1 in the pools, a straight win bet on that horse becomes a solid secondary investment.
Selections
Win: Filled With Desire (POST 4) Place: Cap'n Cats (POST 6) Show: The Fridge (POST 8)
RACE 5 — Post (2:28)/1:28/12:28/11:28 — 1760f | D | M | Md 40000 | BUN | Purse $32,000
A one-mile maiden event for colts and geldings at the $40,000 level — the highest maiden claiming price on the card and a significant step up from the earlier maiden races. With eight runners going a one-turn mile at Parx, this is a distance that tests a horse's class and stamina. The purse of $32,000 attracts legitimate mid-level maidens who have shown some ability at more expensive price tags.
Race 5
Pace Analysis
Off The Deck (POST 6) at 3-1 trained by Guadalupe Preciado with Andy Hernandez is the morning line second choice and figures to be involved near the pace. Sole Lute (POST 8) at 4-1 trained by John Servis with F. Pennington and Sam's Glory (POST 3) at 4-1 trained by Robert Mosco with Francisco Martinez are co-third choices. At a mile, pace scenarios are more nuanced than in shorter sprints, and a horse that can rate comfortably off the lead and have something left for the stretch run is ideal.
Beale Street Boy (POST 2) at 5-1 trained by Jamie Ness with Mychel Sanchez could be a speed type that sets the table. If Beale Street Boy (POST 2) goes to the lead early and establishes an unchallenged pace, he becomes dangerous. Ness is one of the better trainers at Parx and the Sanchez booking on a 5-1 horse at this level is attention-worthy.
Key Contenders
Off The Deck (POST 6) at 3-1 trained by Guadalupe Preciado with Andy Hernandez gets the nod as the top choice in this field. Preciado is among the leading trainers at Parx and has shown a strong ability to condition maiden horses to win at route distances. Post 6 at a one-mile trip at Parx is workable, and Hernandez will have the tactical options to stalk or press depending on the early flow.
Sole Lute (POST 8) at 4-1 trained by John Servis — the senior Servis, one of the most respected conditioners in mid-Atlantic racing — with F. Pennington is a serious contender. Servis rarely enters a horse without a genuine chance of winning, and at 4-1 on the morning line, Sole Lute (POST 8) carries significant stable confidence. The outside post at a mile is not ideal but workable if Pennington can secure a good early position.
Secondary Choices
Beale Street Boy (POST 2) at 5-1 trained by Ness with Sanchez is the secondary play. As noted, the Sanchez booking at 5-1 on a Ness horse at this level is a strong wagering angle. Sam's Glory (POST 3) at 4-1 trained by Mosco with Martinez is a live contender from a workable post. Twooutathreaintbad (POST 4) at 5-1 trained by Kathlee Crook-Demasi with Silvestre Gonzalez is another secondary choice worth including in exotics.
Longshots
Notamistake (POST 5) at 8-1 trained by Guadalupe Preciado with Dexter Haddock gives the Preciado barn two entries in the race. When a conditioner of Preciado's caliber enters two horses in the same race, both deserve respect regardless of price. Arch Competitor (POST 7) at 8-1 trained by Alfredo Velazquez with Carol Cedeno is an interesting longshot, particularly if the pace is honest. St Pete's Passion (POST 1) at 12-1 trained by Clyde Martin with Yan Rodriguez draws the rail in a one-mile trip — somewhat less of a disadvantage than in a shorter sprint — but the 12-1 morning line suggests limited public expectation.
Betting Strategy
This is a race where the double-digit-priced horses backing the Preciado second entry Notamistake (POST 5) could represent genuine value. A trifecta using Off The Deck (POST 6) and Sole Lute (POST 8) as the top two with Beale Street Boy (POST 2), Notamistake (POST 5), and Sam's Glory (POST 3) in the third position slot offers solid coverage at a reasonable price. Win bet on Off The Deck (POST 6) at 3-1 is the primary play.
Selections
Win: Off The Deck (POST 6) Place: Sole Lute (POST 8) Show: Beale Street Boy (POST 2)
RACE 6 — Post (2:55)/1:55/12:55/11:55 — 1320f | D | CO | OClm 25000 | BUN | Purse $32,000
An optional claimer at the $25,000 level for colts and geldings going six furlongs — a solid mid-afternoon race that attracts better horses than the earlier claimers. Six runners make this a manageable field with a clear morning line structure.
Race 6
Pace Analysis
Saint Ephrem (POST 6) and Preacha Meyers (POST 3) are co-morning line favorites at 2-1, which sets up an intriguing pace scenario. Preacha Meyers (POST 3) trained by Jamie Ness with F. Pennington is from post 3 and could be an early speed type. Saint Ephrem (POST 6) trained by Michael Pino with Mychel Sanchez is from the outside in a six-horse field, which is post 6 of 6. If Preacha Meyers (POST 3) controls the early fractions alone, he may be very difficult to beat. If Okie Den Den (POST 2) at 4-1 also wants the lead, the dynamics shift.
Key Contenders
Preacha Meyers (POST 3) at 2-1 trained by Jamie Ness with F. Pennington is a top-shelf contender at this level. Ness is among the elite conditioners at Parx and has an excellent record with optional claimers going sprint distances. Post 3 in a six-horse field is ideal. At 2-1, the price is competitive but Ness horses at this level and distance are worth backing at nearly any odds.
Saint Ephrem (POST 6) at 2-1 trained by Pino with Sanchez is the other co-favorite. As noted throughout this card, the Pino and Sanchez combination is the most powerful pairing at the meet. From post 6 in a six-horse field at six furlongs, Sanchez will need to use some early speed or sit just outside before angling in. Saint Ephrem (POST 6) at 2-1 alongside Preacha Meyers (POST 3) at 2-1 creates an exacta situation where covering both on top of one another is the primary play.
Secondary Choices
Okie Den Den (POST 2) at 4-1 trained by J. Guadalupe Guerrero with Dexter Haddock is the third choice. Post 2 in a six-horse sprint is excellent, and at 4-1, this horse offers clear overlay potential relative to the two co-favorites. If Okie Den Den (POST 2) can secure the lead unchallenged, this horse is live at the price. Musical Maestro (POST 4) at 6-1 trained by Ernesto Padilla-Preciado with Jorge Vargas Jr. is a secondary choice that could hit the board at a good price.
Longshots
Brave Blend (POST 5) at 10-1 trained by Miguel Penaloza with Jean Aguilar is the second-longest price in the field. Whiskeyromeosierra (POST 1) at 12-1 trained by Edward Coletti with Kendry Rivera draws the rail at a long price. Coletti is a lesser-seen trainer at Parx and this entry at 12-1 is primarily of trifecta-deep value only.
Betting Strategy
The exacta covering Preacha Meyers (POST 3) over Saint Ephrem (POST 6) and Saint Ephrem (POST 6) over Preacha Meyers (POST 3) is the core play. Adding Okie Den Den (POST 2) underneath both in trifectas is the recommended structure. If Okie Den Den (POST 2) drifts to 5-1 or higher in the pools, a straight win bet offers compelling value. This race also sets up as a potential win single in Pick sequences with Preacha Meyers (POST 3) as the top choice.
Selections
Win: Preacha Meyers (POST 3) Place: Saint Ephrem (POST 6) Show: Okie Den Den (POST 2)
RACE 7 — Post (3:22)/2:22/1:22/12:22 — 1430f | D | AO | OClm 75000n2l | BOF | Purse $42,000
The consensus best bet race of the card according to multiple handicappers — an optional claimer for $75,000 non-winners of two lifetime going approximately six and a half furlongs on the dirt. The condition non-winners of two lifetime at this price tag typically attracts horses that have demonstrated winning form at least once but have not yet broken through for a second victory. Six runners make this a very manageable field with a clear class structure.
Race 7
Pace Analysis
Divine Seeker (POST 5) at 2-1 trained by Robert Reid Jr. with Abner Adorno is the morning line favorite and the clear horse to beat. Wanna Go Home (POST 1) at 3-1 and Eake (POST 2) and Exciter (POST 3) and Avatude (POST 4) are all clustered at 4-1, which creates an unusually competitive morning line for a six-horse field. The pace picture is where the complexity arises — with multiple horses at short prices, determining who sets the early fractions is critical. Wanna Go Home (POST 1) from the rail trained by Hugo Padilla with Mychel Sanchez figures to be on or near the pace given Sanchez's tendency to secure an early position.
Key Contenders
Divine Seeker (POST 5) at 2-1 trained by Robert Reid Jr. with Abner Adorno is the morning line choice and the consensus selection among handicappers as the best bet of the day. Reid is a respected mid-Atlantic conditioner and Divine Seeker (POST 5) at 2-1 appears to be the horse whose form most clearly fits this condition. Adorno is a competent finisher's rider who can be patient and close ground effectively. Post 5 of 6 in a 1430-foot distance is workable, though it is not ideal — Adorno will need to angle this horse into a comfortable striking position through the turn.
Wanna Go Home (POST 1) at 3-1 trained by Hugo Padilla with Mychel Sanchez is the main danger to the favorite. Sanchez is the leading rider at the meet and from the rail post, he can dictate terms early. Wanna Go Home (POST 1) at 3-1 is the logical bet-against choice or, from the perspective of a bettor who wants to attack the favorite, this is the horse to key as the upset.
Secondary Choices
Eake (POST 2) at 4-1 trained by Guadalupe Preciado with Dexter Haddock represents the Preciado barn in a race where their presence is always a positive sign. Preciado at 75,000 optional claimer level with a 4-1 morning line horse is a sharp entry that demands respect. Exciter (POST 3) at 4-1 trained by Michael Pino with Luis Ocasio is another legitimate contender. Pino with Ocasio in an optional claimer — even if Ocasio is not the barn's primary rider — indicates some stable confidence. Avatude (POST 4) at 4-1 trained by Ernesto Padilla-Preciado with Andy Hernandez is the fourth 4-1 horse in the field and a very live contender. Padilla-Preciado's horses at the optional claimer level often show sharp form and Avatude (POST 4) from post 4 in a six-horse field is ideally positioned.
Longshots
Moon Halory (POST 6) at 10-1 trained by Jose Gonzalez-Milian with A. Castillo is the only genuine longshot in the field. From post 6 in a six-horse race at 1430 feet, this horse will need a pace collapse or a perfect trip to contend. As a single in trifectas, Moon Halory (POST 6) at 10-1 is worth a small investment to add value to exacta/trifecta payouts.
Betting Strategy
This is the race identified as the best bet of the day. Divine Seeker (POST 5) at 2-1 is the primary win bet, but at 2-1, the price demands either a confident win bet or an exacta/trifecta approach that pays more than a single. A structured exacta using Divine Seeker (POST 5) over Wanna Go Home (POST 1), Eake (POST 2), and Avatude (POST 4) covers the main threats at varying prices. If this race is used as a single in a Pick 4 or Pick 5, Divine Seeker (POST 5) alone is defensible at 2-1 given its status as the consensus top selection. Trifecta: Divine Seeker (POST 5) on top, Wanna Go Home (POST 1) and Avatude (POST 4) in second, all remaining in third.
Selections
Win: Divine Seeker (POST 5) Place: Wanna Go Home (POST 1) Show: Avatude (POST 4)
RACE 8 — Post (3:49)/2:49/1:49/12:49 — 1830f | D | AO | OClm 50000b | BUM | Purse $52,000
The featured race of the afternoon — an optional claimer at the $50,000 level going approximately one mile and seventy yards on the dirt. Eight runners and the highest purse on the card make this the prime exotic wagering race of the day. Fillies and mares competing at this optional claiming level typically have demonstrated consistent form and the class to be competitive at a solid mid-level claiming price.
Race 8
Pace Analysis
Sweet Laura (POST 4) is the morning line favorite at 2-1 trained by Jamie Ness with Mychel Sanchez — arguably the single most powerful trainer-jockey combination for this race given Ness and Sanchez's respective credentials at this level. Mary Q (POST 6) at 3-1 trained by Michael Moore with Andy Hernandez is the second choice. A route of a mile and seventy yards will test all runners' stamina, and this race will likely feature a moderate pace with the winner determined in the final furlong.
Lovely Charm (POST 5) at 5-1 trained by Miguel Penaloza with Jorge Vargas Jr. could be involved near the lead. Dancing On My Own (POST 1) at 10-1 trained by Felissa Dunn with Melvis Gonzalez from the rail could also factor early.
Key Contenders
Sweet Laura (POST 4) at 2-1 trained by Ness with Sanchez is the clear favorite and represents the consensus top selection. The Ness and Sanchez combination at this level and distance is the most formidable in the field. Post 4 in an eight-horse route at Parx is ideal — clean break, no early traffic, optimal stalking position. Sweet Laura (POST 4) at 2-1 is defensible as a win single or as the top choice in exactas.
Mary Q (POST 6) at 3-1 trained by Moore with Hernandez is the main challenger. Moore's mares at route distances at Parx have performed well, and Hernandez knows how to rate a horse at a mile-plus distance. From post 6, Mary Q (POST 6) will likely track the pace outside and make a run in the stretch.
Secondary Choices
Lovely Charm (POST 5) at 5-1 trained by Penaloza with Vargas Jr. is a live secondary choice. At 5-1, this mare offers solid value in an exacta structure with either Sweet Laura (POST 4) or Mary Q (POST 6). Delray (POST 3) at 6-1 trained by J. Tyler Servis with Abner Adorno is another legitimate contender — Servis horses at the optional claiming level are worth noting, and Delray (POST 3) from post 3 in a route has an ideal early position.
Jess's Moment (POST 2) at 10-1 trained by Jose Gonzalez-Milian with A. Castillo is an interesting price. Gonzalez-Milian has multiple horses on today's card and the barn is active. At 10-1, this mare has some overlay potential if she is moving forward from her last race.
Longshots
Bella Queen (POST 7) at 8-1 trained by Howard Brown Jr. with Luis Rivera is the highest-priced horse with a realistic shot at a piece of the purse. Dancing On My Own (POST 1) at 10-1 from the rail trained by Dunn with Gonzalez could steal a share if the pace is very slow. Beach Daze (POST 8) at 10-1 trained by Farrel Mann with Adam Bowman is from the outside post in a route and will need a pace to run into. Bowman is capable of getting horses into the race from difficult posts, but 10-1 from post 8 at a route is a hard sell.
Betting Strategy
The featured race warrants the most exotic investment of the afternoon. A win single on Sweet Laura (POST 4) at 2-1 combined with an exacta box of Sweet Laura (POST 4), Mary Q (POST 6), and Lovely Charm (POST 5) covers the main scenarios. For the trifecta, key Sweet Laura (POST 4) and Mary Q (POST 6) on top over the field. Jess's Moment (POST 2) at 10-1 as a third-place finisher in trifectas could produce a meaningful payout. This race is also the anchor for any late Pick 3 or Pick 4 sequences.
Selections
Win: Sweet Laura (POST 4) Place: Mary Q (POST 6) Show: Lovely Charm (POST 5)
RACE 9 — Post (4:16)/3:16/2:16/1:16 — 1210f | D | C | Clm 5000n1y | BUN | Purse $18,000
The card-closing race is a five and a half furlong sprint at the bottom of the claiming ladder — $5,000 claimers that have not won within the last year. With thirteen runners, this is the largest field of the day and is an extremely competitive, chaotic bottom-of-the-barrel sprint that is better suited to exotics than straight betting.
Race 9
Pace Analysis
With thirteen horses in a five and a half furlong sprint, the pace will almost certainly be contested and potentially contested very early. Multiple horses will break looking for a forward position, and the jockeys who can secure a clean trip in the first two furlongs without burning excessive energy will have a significant edge. Post position bias at Parx in sprints of thirteen runners favors the inside if a horse can get clean. Competitive Saint (POST 1) from the rail, Face Down (POST 2), and Cisco Kid (POST 5) are pace-scenario horses to watch.
Key Contenders
Cisco Kid (POST 5) at 4-1 trained by Benjamin Dunn with Melvis Gonzalez is one of the co-favorites and a legitimate top selection in this field. Post 5 in a thirteen-horse sprint at 1210 feet gives a horse the ability to either press or rate without being buried. Amazing Woo (POST 9) at 4-1 trained by Kathlee Crook-Demasi with Abner Adorno is the other co-favorite. Crook-Demasi is an active barn at Parx and Amazing Woo (POST 9) at 4-1 alongside Adorno is a strong combination. Both horses at 4-1 are worth backing in a field of thirteen.
Palm Island (POST 13) at 4-1 trained by Jamie Ness with Mychel Sanchez rounds out the three co-favorites. The Ness and Sanchez connection is powerful regardless of price level, and Palm Island (POST 13) from the extreme outside post in a thirteen-horse field will rely on Sanchez to navigate from whatever position the break allows. In a chaotic field, Sanchez is the rider most capable of manufacturing a trip from an unfavorable post.
Secondary Choices
Face Down (POST 2) at 5-1 trained by Miguel Rodriguez with Dexter Haddock is a secondary play. Post 2 in a thirteen-horse sprint is excellent, and at 5-1, this is a live secondary contender. Competitive Saint (POST 1) at 5-1 trained by Felix Flores-Coba with A. Castillo gets the rail in a five and a half furlong sprint — if this horse breaks alertly, the rail is a significant advantage at Parx. At 5-1, the price is fair and a solid each-way bet is viable.
Longshots
This Run's For You (POST 10) at 10-1 trained by Josue Arce with Francisco Martinez and Time Tested (POST 11) at 10-1 also trained by Arce with Luis Ocasio represent the trainer's double entry at the bottom of this field. Arce with two horses in the same race is always worth noting — at 10-1 each, one of them could be live.
Clever Tiger (POST 3) at 15-1 trained by Steven Krebs with Yan Rodriguez is a price longshot. Curlins Cruzin (POST 4) at 20-1 trained by Pedro Mercedes with Kendry Rivera is a long price from post 4. Dither (POST 6) at 20-1 trained by Jorge Diaz with Noel Herman, Awesome For Sure (POST 7) at 20-1 trained by Joann Bertone with Luis Rivera, Chip's Friend (POST 8) at 20-1 trained by Stephen Hamilton with Adam Bowman, and Omaha Eight (POST 12) at 15-1 trained by Tim Shaw with Silvestre Gonzalez are all at long prices and are primarily of trifecta/superfecta deep consideration only.
Betting Strategy
In a thirteen-horse sprint at the bottom claiming level, the exotic pools are the primary vehicle for profit. A trifecta wheel with Cisco Kid (POST 5), Amazing Woo (POST 9), and Palm Island (POST 13) as the key horses, combined with Face Down (POST 2) and Competitive Saint (POST 1) as fill horses, provides reasonable coverage. A superfecta box of the top five horses at manageable cost is worth considering given the high volatility of a thirteen-horse bottom-claimer sprint. Win bets in this race are speculative; focus on trifectas and superfectas with the three co-favorites as the primary anchors.
Selections
Win: Cisco Kid (POST 5) Place: Amazing Woo (POST 9) Show: Palm Island (POST 13)
Jockey Notes and Insights
Mychel Sanchez is the clear standout among today's rider colony and commands the most important mounts across the card: Mi Hermano (POST 6) in Race 1, Neighbelline (POST 4) in Race 2, Leretha (POST 5) in Race 3, Filled With Desire (POST 4) in Race 4, Beale Street Boy (POST 2) in Race 5, Saint Ephrem (POST 6) in Race 6, Wanna Go Home (POST 1) in Race 7, Sweet Laura (POST 4) in Race 8, and Palm Island (POST 13) in Race 9. Sanchez's book of nine mounts on a nine-race card speaks to his status as the leading rider at the Parx meet. His win percentage at the current meet makes every mount he takes at or near single-digit odds a legitimate wagering proposition.
Kendry Rivera is a capable and active rider at Parx with mounts scattered throughout the card including Gentleman Don (POST 2) in Race 1, Twist Her (POST 1) in Race 2, Global Winner (POST 3) in Race 4, and Whiskeyromeosierra (POST 1) in Race 6. Rivera is a good tactical rider who excels at getting horses into position from shorter sprint distances. His mounts at 4-1 or better are worth close attention.
Andy Hernandez has several key mounts today, most notably Leilauni Sue (POST 1) in Race 3, Off The Deck (POST 6) in Race 5, Avatude (POST 4) in Race 7, and Mary Q (POST 6) in Race 8. Hernandez is a competent professional who handles both sprint and route distances effectively. His assignment on Leilauni Sue (POST 1) and Mary Q (POST 6) indicates trainer confidence in his route ability.
Abner Adorno has a strong book including Lost Love (POST 7) in Race 3, Divine Seeker (POST 5) in Race 7, Delray (POST 3) in Race 8, and Amazing Woo (POST 9) in Race 9. Adorno performs best when given a horse with closing ability, and his mounts today reflect that strength.
Dexter Haddock and Francisco Martinez are two active mid-tier riders with multiple mounts across the card. Haddock rides Okie Den Den (POST 2) in Race 6 and Eake (POST 2) in Race 7 for the Preciado barn, which is always a noteworthy connection. Martinez has mounts in nearly every race and is a versatile rider who functions well in both sprint and route scenarios.
A. Castillo has a busy day with mounts including West Side Diva (POST 2) in Race 3, Its All Gravy (POST 2) in Race 4, Moon Halory (POST 6) in Race 7, and Jess's Moment (POST 2) in Race 8. Castillo is a workmanlike rider at Parx whose mount quality varies widely.
Trainer Notes and Insights
Michael Pino is the premier trainer at Parx Racing today by volume and quality of mounts, with entries in nearly every race: Mi Hermano (POST 6) in Race 1, Filled With Desire (POST 4) and The Fridge (POST 8) in Race 4, Exciter (POST 3) in Race 7, and Saint Ephrem (POST 6) in Race 6. Pino's win percentage at the current meet is among the highest at the track, and his horses are reliably fit and ready to run. Any Pino entry at or near the morning line favorite is a serious play.
Jamie Ness is another elite-level conditioner at Parx with key entries in Beale Street Boy (POST 2) in Race 5, Preacha Meyers (POST 3) in Race 6, Sweet Laura (POST 4) in Race 8, and Palm Island (POST 13) in Race 9. Ness's optional claimer and better claiming horses have excellent records at the current meet, and his combination with Sanchez and with other leading riders is worth watching across the entire card.
Guadalupe Preciado runs a full stable today with entries in Off The Deck (POST 6) and Notamistake (POST 5) in Race 5 and Eake (POST 2) in Race 7. The dual entry in Race 5 is particularly interesting — Preciado does not double-enter without confidence in at least one of the horses, and the trainer's record at route distances at Parx is solid.
Michael Moore is an underrated conditioner at Parx with Leilauni Sue (POST 1) in Race 3, Twist Her (POST 1) in Race 2, and Mary Q (POST 6) in Race 8. Moore's fillies and mares at route and sprint distances perform consistently, and he regularly produces winners at competitive odds.
Uriah St. Lewis has horses at long prices across the card including Global Winner (POST 3) in Race 4 and Flaming Eyes (POST 6) in Race 3. St. Lewis is a smaller barn that occasionally fires with a double-digit priced horse — worth keeping in view when the price warrants a trifecta inclusion.
Kathlee Crook-Demasi has three entries today: Leretha (POST 5) in Race 3, Twooutathreaintbad (POST 4) in Race 5, and Amazing Woo (POST 9) in Race 9. Crook-Demasi is a solid trainer at Parx whose horses at competitive odds tend to run well. The Sanchez booking on Leretha (POST 5) in Race 3 is the most significant of her day.
Robert Reid Jr. with Divine Seeker (POST 5) in Race 7 is the trainer behind the consensus best bet of the card. Reid's record with optional claimers at the non-winners of two conditions is notable at Parx, and his willingness to enter Divine Seeker (POST 5) as the 2-1 morning line choice suggests genuine confidence in the horse's fitness heading into this spot.
Best Wagering Strategies and Value Plays
The Race 7 best bet — Divine Seeker (POST 5) at 2-1 — is the anchor point for the card's Pick 3 and Pick 4 sequences. Structuring a Pick 4 around Races 6, 7, 8, and 9 with Preacha Meyers (POST 3) in Race 6 as a single, Divine Seeker (POST 5) in Race 7 as a single, and Sweet Laura (POST 4) in Race 8 as a single, while spreading in Race 9 across Cisco Kid (POST 5), Amazing Woo (POST 9), Palm Island (POST 13), Face Down (POST 2), and Competitive Saint (POST 1), creates a cost-effective ticket with meaningful potential payouts.
For the Pick 3 in Races 7, 8, and 9, using Divine Seeker (POST 5) as a single in Race 7 and Sweet Laura (POST 4) as a single in Race 8, then spreading wide in Race 9 across five horses, gives a reasonable chance at a Pick 3 that should pay $100 or more depending on the Race 9 winner.
The best straight value plays on the card are Leretha (POST 5) at 5-1 in Race 3, given the Sanchez booking at a price in a field where the favorite is even money, and Okie Den Den (POST 2) at 4-1 in Race 6, which represents the best value in the optional claimer sprint against two co-morning-line favorites.
Exacta plays of note: In Race 6, covering Preacha Meyers (POST 3) and Okie Den Den (POST 2) over Saint Ephrem (POST 6) offers a meaningful payout if the Ness horse wins with the Guerrero horse second. In Race 8, the exacta of Sweet Laura (POST 4) over Lovely Charm (POST 5) at 5-1 is worth a meaningful investment given the gap between those two and the rest of the field.
For bettors looking at the Pick 5, the Parx late Pick 5 typically covers Races 5 through 9. Using Off The Deck (POST 6) as a single in Race 5 if confident, or a two-horse spread with Off The Deck (POST 6) and Sole Lute (POST 8), then Preacha Meyers (POST 3) single in Race 6, Divine Seeker (POST 5) single in Race 7, Sweet Laura (POST 4) single in Race 8, and spreading wide in Race 9 gives a ticket structure that maximizes the potential payout from a likely low-carryover pool. If all five legs hit with primarily favorites, the Pick 5 payout may be modest, but the chaotic nature of Race 9 with thirteen horses at the bottom claiming level ensures the final leg will likely produce a non-trivial return.
The best single value bet of the entire card is Leretha (POST 5) at 5-1 in Race 3 with Mychel Sanchez — a horse at a price with the meet's leading rider in a small field of seven fillies at a middle claiming level. That combination rarely goes uncashed when things go right.
Before wagering, check the Latest Race Scratches, Changes, and Conditions post for any last-minute scratches or race changes.
Get more in-depth analysis for all races and enjoy many other membership perks with a Pick Pony subscription!

✓ Positives:(1) Returning from 33-day layoff with a recent workout. (2) Dropping in class today ($20,000 → $10,000). (3) Early pace significantly above field median (E1: 84 vs field 78). (4) Dropping in class ($10,000 vs last $20,000) after a 33-day freshening — trainer setup-for-win angle. (5) Returning from 33-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (6) Career-best figure (72) buried in races 4–10 back — 20 pts above race median and 12 pts above recent form — market has forgotten the peak effort.