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) Poor record at this distance (0 wins from 7 recent starts). (2) Trip note from last race: Chased 4-5w;weakened. (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) Speed figures are highly erratic over last 5 starts (σ = 16.0 pts: [39, 62, 60, 69, 83]) — unpredictable performer. (6) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 79 (4/7) Mod2(W): 84 (4/7) Mod3(W): 79 (4/7) Mod1-LS: 63 (6/7) Mod2-LS: 79 (4/7) Mod3-LS: 9 (6/7) Mod4(Form): 77 (4/7) Win Prob: 35.5% Value Score: 2.47 ★ ML: 4.50 (7/2) Overlay %: -0.31 Fair Odds: 6.12 (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 | B | F |
| Early Pace | D | C |
| Mid Pace | B | C |
| Late Pace | B | D |
| Finish Pos | B | D |
| Dirt Speed | B | D |
| Turf Speed | C | D |
| Distance Speed | A | C |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | D | 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 | B | F |
| Early Pace | B | C |
| Mid Pace | B | C |
| Late Pace | A | D |
| Sprint FPS | D | B |
| Route FPS | A | A |
| Trainer Effectiveness | F | F |
| Jockey Effectiveness | D | 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 | D | F |
| Early Pace | D | 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) Hot trainer - high ITM rate (54%). (2) Strong trainer/jockey combo - 4 wins from 10 starts (40%). (3) Career-best speed figure (65) recorded in last 1-2 starts — peaking form. (4) Hot jockey — high ITM rate (39%). (5) Early pace significantly above field median (E1: 87 vs field 82). (6) Strong speed 2 back (65), modest dip last out (57) — form reversal angle, ready to bounce back to top form. (7) Dropping in class ($7,500 vs last $10,000) after a 89-day freshening — trainer setup-for-win angle. (8) Averages 58.5 speed pts in today's distance/surface configuration vs 52.7 in other configs (6 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Has not raced in 89 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Poor record at this distance (0 wins from 6 recent starts). (4) Trip note from last race: Press btwn 3w;gave way. (5) 0 wins from 9 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 87 (3/7) Mod2(W): 99 (2/7) Mod3(W): 82 (3/7) Mod1-LS: 85 (2/7) Mod2-LS: 100 (1/7) Mod3-LS: 100 (1/7) Mod4(Form): 96 (2/7) Win Prob: 57.2% Value Score: 2.9 ★ ML: 3.00 (2/1) Overlay %: -4.51 Fair Odds: 5.57 (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 | B |
| Mid Pace | A | B |
| Late Pace | B | D |
| Finish Pos | B | C |
| Dirt Speed | A | C |
| Turf Speed | C | D |
| Distance Speed | A | C |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | C |
| 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 | A | A |
| Mid Pace | A | B |
| Late Pace | A | D |
| Sprint FPS | B | A |
| Route FPS | C | B |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | C |
| 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 | B | F |
| Early Pace | A | A |
| 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) Hot jockey — high ITM rate (38%). (2) Late pace significantly above field median (LP: 67 vs field 60). (3) Career-best figure (80) buried in races 4–10 back — 25 pts above race median and 12 pts above recent form — market has forgotten the peak effort.
⚠ Concerns:(1) Poor record at this distance (0 wins from 10 recent starts). (2) Trip note from last race: Shuffled to turn;2-3w. (3) Post 8 in a 8-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (4) Speed figures are highly erratic over last 5 starts (σ = 15.9 pts: [43, 44, 68, 80, 55]) — unpredictable performer. (5) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 100 (1/7) Mod2(W): 100 (1/7) Mod3(W): 96 (2/7) Mod1-LS: 85 (3/7) Mod2-LS: 90 (2/7) Mod3-LS: 42 (5/7) Mod4(Form): 100 (1/7) Win Prob: 49.8% Value Score: 2.21 ★ ML: 2.50 (3/2) Overlay %: -8.14 Fair Odds: 5.93 (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 | B | F |
| Early Pace | C | C |
| Mid Pace | C | D |
| Late Pace | A | D |
| Finish Pos | A | C |
| Dirt Speed | C | D |
| Turf Speed | C | D |
| Distance Speed | B | C |
| Trainer Effectiveness | C | F |
| Jockey Effectiveness | A | C |
| 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 | B | F |
| Early Pace | D | C |
| Mid Pace | C | D |
| Late Pace | B | D |
| Sprint FPS | A | A |
| Route FPS | A | A |
| Trainer Effectiveness | C | F |
| Jockey Effectiveness | A | C |
| 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 | C | F |
| Early Pace | D | C |
| 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) Career-best figure (63) buried in races 4–10 back — 12 pts above race median and 5 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) Poor record at this distance (0 wins from 6 recent starts). (3) Trip note from last race: Stp slw;chsd ins;empty. (4) Speed figures are highly erratic over last 5 starts (σ = 13.1 pts: [34, 48, 58, 63, 35]) — unpredictable performer. (5) 0 wins from 7 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 65 (5/8) Mod2(W): 53 (6/8) Mod3(W): 53 (5/8) Mod1-LS: 93 (4/8) Mod2-LS: 46 (6/8) Mod3-LS: 63 (6/8) Mod4(Form): 40 (5/8) Win Prob: 36.2% Value Score: 4.17 ★ ML: 8.00 (7/1) Overlay %: 9.84 Fair Odds: 4.40 (7/2) 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 | A | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | F |
| Early Pace | B | C |
| Mid Pace | B | D |
| Late Pace | C | D |
| Finish Pos | B | A |
| Dirt Speed | B | D |
| Turf Speed | A | C |
| Distance Speed | D | F |
| Trainer Effectiveness | B | C |
| Jockey Effectiveness | C | F |
| 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 | D | F |
| Early Pace | A | B |
| Mid Pace | A | C |
| Late Pace | D | D |
| Sprint FPS | A | A |
| Route FPS | A | A |
| Trainer Effectiveness | B | C |
| Jockey Effectiveness | C | F |
| 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 | C | F |
| Early Pace | C | 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) Dropping in class today ($12,500 → $7,500). (2) Hot trainer - high ITM rate (47%). (3) Hot jockey — high ITM rate (48%). (4) In the money in last 3 consecutive starts. (5) Late pace significantly above field median (LP: 68 vs field 63). (6) Closer/presser in a race with pace pressure — ideal race setup for late runners. (7) Dropping in class ($7,500 vs last $12,500) after a 76-day freshening — trainer setup-for-win angle. (8) Career-best figure (64) buried in races 4–10 back — 14 pts above race median and 6 pts above recent form — market has forgotten the peak effort. (9) Had documented trouble last race (codes: ['B', 'D', 'S', 'T', 'U']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 76 days. (2) Poor record at this distance (0 wins from 8 recent starts). (3) Trip note from last race: Ins-2w;sustained bid. (4) Consistently breaks behind post position (3 of last 5 starts). (5) Consistently runs wide at the first call (3 of last 5 starts). (6) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 88 (3/8) Mod2(W): 100 (1/8) Mod3(W): 97 (2/8) Mod1-LS: 86 (5/8) Mod2-LS: 100 (1/8) Mod3-LS: 81 (4/8) Mod4(Form): 100 (1/8) Win Prob: 68.8% Value Score: 3.08 ★ ML: 2.50 (3/2) Overlay %: -9.84 Fair Odds: 7.00 (6/1) 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 | F |
| Early Pace | C | D |
| Mid Pace | B | D |
| Late Pace | A | D |
| Finish Pos | B | A |
| Dirt Speed | B | C |
| Turf Speed | C | D |
| Distance Speed | A | C |
| Trainer Effectiveness | A | B |
| 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 | A | F |
| Early Pace | D | D |
| Mid Pace | C | D |
| Late Pace | A | C |
| Sprint FPS | D | D |
| Route FPS | C | C |
| Trainer Effectiveness | A | B |
| 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 | A | D |
| Early Pace | D | 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) Big last-race effort (57) — 15 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 64-day layoff — often the peak fitness race. (4) Trainer 'HUDSON JEFF' has 3 horses in today's card all showing last-race improvement — barn appears sharp right now. (5) Had documented trouble last race (codes: ['D', 'L', 'O', 'S']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Repeatedly beaten at this class level (3 of last 5 starts). (2) Speed average (44) well below field median (50). (3) Poor record at this distance (0 wins from 6 recent starts). (4) Trip note from last race: Closed inside;mssd 2nd. (5) Last race was career-best speed (57) — bounce risk after peak effort. (6) Speed figures are highly erratic over last 5 starts (σ = 12.5 pts: [57, 54, 47, 25, 46]) — unpredictable performer. (7) 0 wins from 6 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 80 (4/8) Mod2(W): 81 (4/8) Mod3(W): 87 (4/8) Mod1-LS: 72 (6/8) Mod2-LS: 77 (4/8) Mod3-LS: 60 (7/8) Mod4(Form): 74 (4/8) Win Prob: 48.4% Value Score: 3.41 ★ ML: 4.50 (7/2) Overlay %: -2.97 Fair Odds: 7.89 (7/1) 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 | C | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | F |
| Early Pace | D | D |
| Mid Pace | C | D |
| Late Pace | C | D |
| Finish Pos | B | A |
| Dirt Speed | C | D |
| Turf Speed | C | D |
| Distance Speed | B | C |
| Trainer Effectiveness | D | F |
| Jockey Effectiveness | D | F |
| 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 | C | C |
| Mid Pace | B | D |
| Late Pace | B | D |
| Sprint FPS | C | C |
| Route FPS | B | B |
| Trainer Effectiveness | D | F |
| Jockey Effectiveness | D | F |
| 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 | C | F |
| Early Pace | D | D |
| 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) Hot trainer - high ITM rate (44%). (2) Big last-race effort (65) — 18 pts above recent average. (3) Hot jockey — high ITM rate (42%). (4) Closer/presser in a race with pace pressure — ideal race setup for late runners. (5) Had documented trouble last race (codes: ['B', 'D', 'F', 'T', 'U']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Repeatedly beaten at this class level (3 of last 5 starts). (2) Poor record at this distance (0 wins from 8 recent starts). (3) Trip note from last race: Traffic 2nd turn;bid. (4) Last race was career-best speed (65) — bounce risk after peak effort. (5) Post 9 in a 9-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (6) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 90 (2/8) Mod2(W): 98 (2/8) Mod3(W): 100 (1/8) Mod1-LS: 94 (2/8) Mod2-LS: 95 (2/8) Mod3-LS: 84 (3/8) Mod4(Form): 86 (2/8) Win Prob: 61% Value Score: 3.51 ★ ML: 3.50 (5/2) Overlay %: -5.24 Fair Odds: 7.24 (6/1) 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 | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | F |
| Early Pace | B | C |
| Mid Pace | C | D |
| Late Pace | B | D |
| Finish Pos | B | A |
| Dirt Speed | A | C |
| Turf Speed | C | D |
| Distance Speed | A | C |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | A | C |
| 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 | B | C |
| Mid Pace | C | D |
| Late Pace | C | D |
| Sprint FPS | C | D |
| Route FPS | C | C |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | A | C |
| 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 | B | F |
| 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) Hot trainer - high ITM rate (47%). (2) Career-best speed figure (64) recorded in last 1-2 starts — peaking form. (3) Hot jockey — high ITM rate (48%). (4) Strong speed 2 back (64), modest dip last out (58) — form reversal angle, ready to bounce back to top form.
⚠ Concerns:(1) Consider there will be likely pace pressure in this race - multiple E types entered. (2) Tends to fade in the stretch at similar distances (2 of 3 starts). (3) Trip note from last race: Stalk 2w-ins;weakened. (4) Was the betting favorite in the last race but finished off the board. (5) No workout in last 30 days despite 21 days since last race.
Mod1(W): 77 (3/7) Mod2(W): 64 (3/7) Mod3(W): 80 (3/7) Mod1-LS: 100 (1/7) Mod2-LS: 63 (3/7) Mod3-LS: 100 (1/7) Mod4(Form): 42 (5/7) Win Prob: 24.8% Value Score: 2.2 ★ ML: 8.00 (7/1) Overlay %: -0.03 Fair Odds: 7.89 (7/1) 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 | F |
| Early Pace | C | C |
| Mid Pace | A | C |
| Late Pace | C | D |
| Finish Pos | F | F |
| Dirt Speed | B | C |
| Turf Speed | C | D |
| Distance Speed | F | F |
| Trainer Effectiveness | B | B |
| 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 | B | D |
| Early Pace | A | B |
| Mid Pace | A | C |
| Late Pace | C | D |
| Sprint FPS | D | A |
| Route FPS | B | A |
| Trainer Effectiveness | B | B |
| 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 | B | F |
| 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) Career-best speed figure (62) recorded in last 1-2 starts — peaking form. (2) Hot jockey — high ITM rate (38%). (3) Has won at today's distance (990 yds) within the last 10 starts — proven ability at this trip. (4) Had documented trouble last race (codes: ['B', 'D', 'S', 'T', 'V']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Rising in class today ($5,000 → $7,500). (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Trip note from last race: Vied 3w;game;bested. (4) Speed figures are highly erratic over last 5 starts (σ = 11.4 pts: [62, 82, 70, 64, 51]) — unpredictable performer.
Mod1(W): 96 (2/7) Mod2(W): 100 (1/7) Mod3(W): 100 (2/7) Mod1-LS: 68 (3/7) Mod2-LS: 100 (1/7) Mod3-LS: 50 (3/7) Mod4(Form): 100 (1/7) Win Prob: 69.2% Value Score: 2.73 ★ ML: 3.00 (2/1) Overlay %: -2.16 Fair Odds: 3.31 (5/2) 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 | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | D |
| Early Pace | A | B |
| Mid Pace | C | D |
| Late Pace | D | D |
| Finish Pos | A | C |
| Dirt Speed | D | D |
| Turf Speed | C | D |
| Distance Speed | B | C |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | B | C |
| 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 | A | C |
| Early Pace | B | B |
| Mid Pace | D | D |
| Late Pace | B | D |
| Sprint FPS | A | A |
| Route FPS | A | A |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | B | C |
| 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 | D |
| 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) Late pace significantly above field median (LP: 67 vs field 63). (2) Fourth race back from a 55-day layoff — often the peak fitness race. (3) Has won at today's distance (990 yds) within the last 10 starts — proven ability at this trip. (4) Has won at SRP on dirt in the last 10 starts — proven at today's exact track/surface combo. (5) Career-best figure (69) buried in races 4–10 back — 11 pts above race median and 7 pts above recent form — market has forgotten the peak effort. (6) Had documented trouble last race (codes: ['F', 'O', 'S', 'T', 'U']) 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: 5-4w;2w-ins;outfinish. (3) Has not won in last 10 starts despite career wins.
Mod1(W): 100 (1/7) Mod2(W): 89 (2/7) Mod3(W): 100 (1/7) Mod1-LS: 76 (2/7) Mod2-LS: 90 (2/7) Mod3-LS: 36 (5/7) Mod4(Form): 86 (2/7) Win Prob: 45.8% Value Score: 2.25 ★ ML: 4.00 (3/1) Overlay %: -7.48 Fair Odds: 6.80 (6/1) 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 | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | D |
| Early Pace | B | B |
| Mid Pace | A | B |
| Late Pace | A | D |
| Finish Pos | B | C |
| Dirt Speed | A | C |
| Turf Speed | C | D |
| Distance Speed | B | C |
| Trainer Effectiveness | B | C |
| Jockey Effectiveness | D | 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 | B | B |
| Mid Pace | A | C |
| Late Pace | A | C |
| Sprint FPS | D | A |
| Route FPS | D | B |
| Trainer Effectiveness | B | C |
| Jockey Effectiveness | D | 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 | A | D |
| 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) Returning from 61-day layoff with a recent workout. (2) Hot trainer - high ITM rate (49%). (3) Career-best speed figure (57) recorded in last 1-2 starts — peaking form. (4) Early pace significantly above field median (E1: 87 vs field 83). (5) Returning from 61-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (6) Had documented trouble last race (codes: ['D', 'L']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 61 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Poor record at this distance (0 wins from 5 recent starts). (4) Tends to fade in the stretch at similar distances (3 of 5 starts). (5) Trip note from last race: 4-w; mild rally. (6) 0 wins from 5 starts on dirt in last 10 — repeated failure on today's surface. (7) First start at SRP — never raced here before (last seen at: SUN, ZIA).
Mod1(W): 100 (1/11) Mod2(W): 85 (3/11) Mod3(W): 99 (2/11) Mod1-LS: 68 (7/11) Mod2-LS: 81 (3/11) Mod3-LS: 59 (2/11) Mod4(Form): 97 (2/11) Win Prob: 53.9% Value Score: 3.38 ★ ML: 3.50 (5/2) Overlay %: -6.35 Fair Odds: 9.40 (8/1) 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 | F |
| Early Pace | A | B |
| Mid Pace | A | C |
| Late Pace | B | D |
| Finish Pos | A | D |
| Dirt Speed | C | D |
| Turf Speed | C | D |
| Distance Speed | A | 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 | B | F |
| Early Pace | B | B |
| Mid Pace | B | C |
| Late Pace | B | D |
| Sprint FPS | A | A |
| Route FPS | A | A |
| 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 | A | F |
| 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) Speed average (61) well above field median (51). (2) Career-best speed figure (49) recorded in last 1-2 starts — peaking form. (3) Equipment change today (code: 1). (4) Hot jockey — high ITM rate (42%). (5) Closer/presser in a race with pace pressure — ideal race setup for late runners. (6) One gate workout in recent training — sharpness signal from the gate. (7) Returning from 76-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (8) Career-best figure (85) buried in races 4–10 back — 34 pts above race median and 16 pts above recent form — market has forgotten the peak effort. (9) Had documented trouble last race (codes: ['D', 'F', 'L', 'S', 'T', 'U']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 76 days. (2) Trip note from last race: Shuffled st;2w;up 3rd. (3) First start at SRP — never raced here before (last seen at: SUN).
Mod1(W): 96 (2/11) Mod2(W): 98 (2/11) Mod3(W): 99 (3/11) Mod1-LS: 80 (5/11) Mod2-LS: 100 (1/11) Mod3-LS: 38 (6/11) Mod4(Form): 83 (3/11) Win Prob: 53.3% Value Score: 4.08 ★ ML: 4.50 (7/2) Overlay %: -3.66 Fair Odds: 9.64 (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 | D |
| Early Pace | B | B |
| Mid Pace | A | A |
| Late Pace | D | F |
| Finish Pos | A | D |
| Dirt Speed | C | D |
| Turf Speed | C | D |
| Distance Speed | B | D |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | A | C |
| 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 | B |
| Mid Pace | A | A |
| Late Pace | D | F |
| Sprint FPS | C | C |
| Route FPS | A | A |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | A | C |
| 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 | C | C |
| Mid Pace | D | 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 trainer - high ITM rate (47%). (2) Big last-race effort (62) — 16 pts above recent average. (3) Has a bullet work (fastest at track that day) — sharp conditioning signal. (4) Early pace significantly above field median (E1: 90 vs field 83). (5) Had documented trouble last race (codes: ['B', 'D', 'S', 'T', 'V']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Rising in class today ($7,500 → $12,500). (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: Vied inside; 2nd best. (5) Last race was career-best speed (62) — bounce risk after peak effort. (6) Stepping up to $12,500 — highest class level in last 10 starts (previous high: $7,500).
Mod1(W): 87 (4/11) Mod2(W): 78 (4/11) Mod3(W): 93 (4/11) Mod1-LS: 73 (6/11) Mod2-LS: 69 (4/11) Mod3-LS: 100 (1/11) Mod4(Form): 63 (4/11) Win Prob: 49.3% Value Score: 4.81 ★ ML: 6.00 (5/1) Overlay %: 5.68 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 | A | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | F |
| Early Pace | A | A |
| Mid Pace | A | B |
| Late Pace | D | F |
| Finish Pos | D | F |
| Dirt Speed | A | D |
| Turf Speed | C | D |
| Distance Speed | D | F |
| Trainer Effectiveness | B | B |
| 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 | C | F |
| Early Pace | A | A |
| Mid Pace | A | B |
| Late Pace | D | D |
| Sprint FPS | A | A |
| Route FPS | A | A |
| Trainer Effectiveness | B | B |
| 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 | F |
| Early Pace | A | A |
| 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 (58) well above field median (51). (2) Career-best speed figure (65) recorded in last 1-2 starts — peaking form. (3) Late pace significantly above field median (LP: 62 vs field 59). (4) Returning from 111-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (5) Career-best figure (77) buried in races 4–10 back — 26 pts above race median and 8 pts above recent form — market has forgotten the peak effort. (6) Averages 60.8 speed pts in today's distance/surface configuration vs 49.0 in other configs (8 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Has not raced in 111 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Poor record at this distance (0 wins from 8 recent starts). (4) Trip note from last race: Stalk;5p;faded. (5) Outside post (8) in a large field of 12 horses. (6) No workout in last 30 days despite 111 days since last race. (7) Post 8 in a 12-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): 76 (5/11) Mod2(W): 53 (6/11) Mod3(W): 63 (7/11) Mod1-LS: 100 (1/11) Mod2-LS: 46 (7/11) Mod3-LS: 28 (9/11) Mod4(Form): 45 (5/11) Win Prob: 19.1% Value Score: 2.4 ★ ML: 8.00 (7/1) Overlay %: 0.30 Fair Odds: 11.08 (10/1) 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 | A | D |
| Early Pace | B | B |
| Mid Pace | B | C |
| Late Pace | B | D |
| Finish Pos | C | F |
| Dirt Speed | A | C |
| Turf Speed | C | D |
| Distance Speed | A | C |
| Trainer Effectiveness | C | C |
| Jockey Effectiveness | D | F |
| 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 | A | A |
| Mid Pace | B | C |
| Late Pace | B | D |
| Sprint FPS | C | B |
| Route FPS | C | C |
| Trainer Effectiveness | C | C |
| Jockey Effectiveness | D | F |
| 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 | A | B |
| Mid Pace | D | 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 40-day layoff with a recent workout. (2) Strong trainer/jockey combo - 4 wins from 7 starts (57%). (3) Career-best speed figure (69) 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) Strong speed 2 back (69), modest dip last out (60) — form reversal angle, ready to bounce back to top form. (7) Returning from 40-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (8) Had documented trouble last race (codes: ['B', 'D', 'O', 'T', 'U']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 40 days. (2) Rising in class today ($8,000 → $12,500). (3) Consider there will be likely pace pressure in this race - multiple E types entered. (4) Speed average (42) well below field median (51). (5) Poor record at this distance (0 wins from 5 recent starts). (6) Trip note from last race: Pace btwn 2w;outkicked. (7) Outside post (10) in a large field of 12 horses. (8) Post 10 in a 12-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 = 10.5 pts: [60, 69, 47, 48, 44]) — unpredictable performer. (10) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 89 (3/11) Mod2(W): 100 (1/11) Mod3(W): 100 (1/11) Mod1-LS: 81 (4/11) Mod2-LS: 90 (2/11) Mod3-LS: 43 (4/11) Mod4(Form): 100 (1/11) Win Prob: 41.3% Value Score: 2.3 ★ ML: 3.00 (2/1) Overlay %: -8.16 Fair Odds: 9.20 (8/1) 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 | D | F |
| Early Pace | D | C |
| Mid Pace | D | D |
| Late Pace | C | D |
| Finish Pos | C | F |
| Dirt Speed | A | C |
| Turf Speed | C | D |
| Distance Speed | C | D |
| Trainer Effectiveness | C | B |
| Jockey Effectiveness | A | A |
| 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 | C |
| Mid Pace | D | D |
| Late Pace | A | C |
| Sprint FPS | B | B |
| Route FPS | B | A |
| Trainer Effectiveness | C | B |
| Jockey Effectiveness | A | A |
| 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 | D | F |
| Early Pace | B | C |
| 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) Equipment change today (code: 1). (2) Early pace significantly above field median (E1: 89 vs field 85). (3) Had documented trouble last race (codes: ['D', 'L', 'S']) 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) Limited experience at today's distance (1 start). (3) Trip note from last race: Press 2w;led;yielded. (4) No workout in last 30 days despite 21 days since last race. (5) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 96 (3/9) Mod2(W): 71 (3/9) Mod3(W): 84 (3/9) Mod1-LS: 54 (5/9) Mod2-LS: 71 (3/9) Mod3-LS: 65 (2/9) Mod4(Form): 81 (3/9) Win Prob: 48% Value Score: 3.42 ★ ML: 4.50 (7/2) Overlay %: -0.29 Fair Odds: 6.29 (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 | C | D |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | F | D |
| Finish Pos | D | F |
| Dirt Speed | A | A |
| Turf Speed | C | D |
| Distance Speed | B | C |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | D | F |
| 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 | A | A |
| Mid Pace | A | B |
| Late Pace | B | C |
| Sprint FPS | A | A |
| Route FPS | A | A |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | D | F |
| 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 | 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 69-day layoff with a recent workout. (2) Hot trainer - high ITM rate (53%). (3) Career-best speed figure (79) recorded in last 1-2 starts — peaking form. (4) Big last-race effort (69) — 8 pts above recent average. (5) Hot jockey — high ITM rate (38%). (6) Has a bullet work (fastest at track that day) — sharp conditioning signal. (7) Early pace significantly above field median (E1: 88 vs field 85). (8) Strong speed 2 back (79), modest dip last out (69) — form reversal angle, ready to bounce back to top form. (9) Has won at today's distance (990 yds) within the last 10 starts — proven ability at this trip. (10) Returning from 69-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (11) Trainer 'FINCHER TODD W' 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', 'V']) yet still finished 2nd — a clean trip today sets up a form reversal. (13) Averages 65.7 speed pts in today's distance/surface configuration vs 56.7 in other configs (7 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Has not raced in 69 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Trip note from last race: Stalk 2w;saved 2nd. (4) Speed figures are highly erratic over last 5 starts (σ = 11.7 pts: [69, 79, 50, 54, 66]) — unpredictable performer.
Mod1(W): 98 (2/9) Mod2(W): 76 (2/9) Mod3(W): 88 (2/9) Mod1-LS: 59 (3/9) Mod2-LS: 74 (2/9) Mod3-LS: 100 (1/9) Mod4(Form): 94 (2/9) Win Prob: 68.8% Value Score: 4.02 ★ ML: 3.50 (5/2) Overlay %: -7.30 Fair Odds: 9.17 (8/1) 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 | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | D |
| Early Pace | A | A |
| Mid Pace | A | A |
| Late Pace | D | D |
| Finish Pos | B | C |
| Dirt Speed | C | B |
| Turf Speed | C | D |
| Distance Speed | C | D |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | C |
| 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 | A | A |
| Mid Pace | A | A |
| Late Pace | D | D |
| Sprint FPS | C | A |
| Route FPS | B | A |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | C |
| 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 | C | D |
| 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) Speed average (76) well above field median (64). (2) Hot trainer - high ITM rate (60%). (3) Big last-race effort (87) — 9 pts above recent average. (4) Hot jockey — high ITM rate (39%). (5) In the money in last 5 consecutive starts. (6) Late pace significantly above field median (LP: 75 vs field 70). (7) Has won at today's distance (990 yds) within the last 10 starts — proven ability at this trip. (8) Career-best figure (96) buried in races 4–10 back — 32 pts above race median and 9 pts above recent form — market has forgotten the peak effort. (9) Had documented trouble last race (codes: ['O', '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: Rough start;4-5w turn. (3) Outside post (8) in a large field of 10 horses. (4) Last race was career-best speed (87) — bounce risk after peak effort. (5) No workout in last 30 days despite 20 days since last race. (6) Post 8 in a 10-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 = 9.6 pts: [87, 72, 76, 87, 96]) — unpredictable performer.
Mod1(W): 100 (1/9) Mod2(W): 100 (1/9) Mod3(W): 100 (1/9) Mod1-LS: 100 (1/9) Mod2-LS: 100 (1/9) Mod3-LS: 65 (3/9) Mod4(Form): 100 (1/9) Win Prob: 67.4% Value Score: 3.5 ★ ML: 3.00 (2/1) Overlay %: -7.98 Fair Odds: 7.86 (7/1) 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 | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | B |
| Early Pace | C | B |
| Mid Pace | D | C |
| Late Pace | A | B |
| Finish Pos | A | B |
| Dirt Speed | D | B |
| Turf Speed | C | D |
| Distance Speed | A | C |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | 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 | A | B |
| Early Pace | B | B |
| Mid Pace | D | C |
| Late Pace | A | B |
| Sprint FPS | B | A |
| Route FPS | D | B |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | 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 | A | B |
| Early Pace | D | 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) Speed average (71) well above field median (64). (2) Strong trainer/jockey combo - 2 wins from 6 starts (33%). (3) Late pace significantly above field median (LP: 75 vs field 70). (4) Has won at today's distance (990 yds) within the last 10 starts — proven ability at this trip. (5) Had documented trouble last race (codes: ['D', 'S', 'V']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 151 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: Prsd pc;4p;gave way. (5) Outside post (9) in a large field of 10 horses. (6) Post 9 in a 10-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (7) First start at SRP — never raced here before (last seen at: ZIA, ALB).
Mod1(W): 55 (4/9) Mod2(W): 49 (4/9) Mod3(W): 44 (5/9) Mod1-LS: 38 (7/9) Mod2-LS: 46 (4/9) Mod3-LS: 0 Mod4(Form): 62 (4/9) Win Prob: 44.7% Value Score: 4.06 ★ ML: 6.00 (5/1) Overlay %: -2.57 Fair Odds: 10.84 (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 | C | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | C |
| Early Pace | C | B |
| Mid Pace | B | B |
| Late Pace | A | B |
| Finish Pos | B | C |
| Dirt Speed | B | B |
| Turf Speed | A | A |
| Distance Speed | D | F |
| Trainer Effectiveness | B | B |
| 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 | A | C |
| Early Pace | C | C |
| Mid Pace | B | B |
| Late Pace | A | B |
| Sprint FPS | D | A |
| Route FPS | A | A |
| Trainer Effectiveness | B | B |
| 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 | 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) Returning from 66-day layoff with a recent workout. (2) Hot jockey — high ITM rate (38%). (3) In the money in last 5 consecutive starts. (4) Has a bullet work (fastest at track that day) — sharp conditioning signal. (5) Returning from 66-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (6) Had documented trouble last race (codes: ['D', 'L']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 66 days. (2) Poor record at this distance (0 wins from 10 recent starts). (3) Trip note from last race: Rallied; 4w; willingly. (4) Has not won in last 10 starts despite career wins. (5) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 100 (1/7) Mod2(W): 82 (2/7) Mod3(W): 67 (4/7) Mod1-LS: 55 (3/7) Mod2-LS: 83 (2/7) Mod3-LS: 38 (4/7) Mod4(Form): 95 (2/7) Win Prob: 42.3% Value Score: 2.14 ★ ML: 3.00 (2/1) Overlay %: -5.88 Fair Odds: 6.22 (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 | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | C |
| Early Pace | D | D |
| Mid Pace | D | C |
| Late Pace | B | A |
| Finish Pos | A | C |
| Dirt Speed | A | A |
| Turf Speed | A | A |
| Distance Speed | D | B |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | B | C |
| 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 | B |
| Early Pace | D | D |
| Mid Pace | D | C |
| Late Pace | A | A |
| Sprint FPS | D | D |
| Route FPS | D | D |
| Trainer Effectiveness | D | D |
| Jockey Effectiveness | B | C |
| 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 | C |
| 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) Speed average (77) well above field median (68). (2) Hot trainer - high ITM rate (47%). (3) Career-best speed figure (85) recorded in last 1-2 starts — peaking form. (4) Hot jockey — high ITM rate (39%). (5) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip. (6) Had documented trouble last race (codes: ['D', 'O', 'S']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Was claimed from its most recent race - new connections. (2) Trip note from last race: Chased 5w;needed more. (3) Dropping in class in consecutive starts ($15,000 → $10,000 → $7,500). (4) Speed figures are highly erratic over last 5 starts (σ = 10.3 pts: [65, 92, 72, 71, 71]) — unpredictable performer.
Mod1(W): 96 (2/7) Mod2(W): 100 (1/7) Mod3(W): 100 (1/7) Mod1-LS: 100 (1/7) Mod2-LS: 100 (1/7) Mod3-LS: 44 (3/7) Mod4(Form): 100 (1/7) Win Prob: 68.9% Value Score: 3.05 ★ ML: 2.50 (3/2) Overlay %: -7.63 Fair Odds: 5.70 (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 | B |
| Early Pace | B | B |
| Mid Pace | A | B |
| Late Pace | A | A |
| Finish Pos | A | B |
| Dirt Speed | D | A |
| Turf Speed | D | D |
| Distance Speed | B | B |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | A | C |
| 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 | B | B |
| Mid Pace | A | B |
| Late Pace | B | B |
| Sprint FPS | C | B |
| Route FPS | B | B |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | A | C |
| 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 | A | 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) Track specialist — 2 wins from 8 starts here (25%). (2) Had documented trouble last race (codes: ['D', 'L', 'S', 'T', 'U']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Rising in class today ($5,000 → $7,500). (2) Speed average (61) well below field median (68). (3) Poor record at this distance (0 wins from 6 recent starts). (4) Trip note from last race: 3wd sustained rally. (5) Has not won in last 10 starts despite career wins. (6) Rising in class ($5,000 → $7,500) after finishing 3 last out — double negative. (7) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface.
Mod1(W): 93 (3/7) Mod2(W): 60 (4/7) Mod3(W): 68 (3/7) Mod1-LS: 0 Mod2-LS: 56 (4/7) Mod3-LS: 46 (2/7) Mod4(Form): 87 (3/7) Win Prob: 42.7% Value Score: 2.43 ★ ML: 3.50 (5/2) Overlay %: -3.91 Fair Odds: 6.33 (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 | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | F | D |
| Early Pace | D | D |
| Mid Pace | F | D |
| Late Pace | D | C |
| Finish Pos | F | F |
| Dirt Speed | B | A |
| Turf Speed | D | D |
| Distance Speed | A | A |
| Trainer Effectiveness | D | F |
| 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 | D | D |
| Mid Pace | D | D |
| Late Pace | C | B |
| Sprint FPS | D | D |
| Route FPS | C | C |
| Trainer Effectiveness | D | F |
| 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 | D | D |
| Early Pace | D | D |
| 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 (53%). (2) Hot jockey — high ITM rate (42%). (3) Early pace significantly above field median (E1: 88 vs field 84). (4) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip. (5) Had documented trouble last race (codes: ['D', 'L', 'O']) yet still finished 3rd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Rising in class today ($5,000 → $7,500). (2) Trip note from last race: Rallied; 4w; no menace. (3) No workout in last 30 days despite 27 days since last race. (4) Rising in class ($5,000 → $7,500) after finishing 3 last out — double negative. (5) Post 8 in a 8-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (6) Speed figures are highly erratic over last 5 starts (σ = 10.6 pts: [56, 62, 79, 80, 73]) — unpredictable performer.
Mod1(W): 91 (4/7) Mod2(W): 65 (3/7) Mod3(W): 76 (2/7) Mod1-LS: 36 (4/7) Mod2-LS: 64 (3/7) Mod3-LS: 100 (1/7) Mod4(Form): 74 (4/7) Win Prob: 50.9% Value Score: 3.54 ★ ML: 4.50 (7/2) Overlay %: -0.98 Fair Odds: 6.48 (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 | B |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | D | D |
| Early Pace | A | B |
| Mid Pace | A | A |
| Late Pace | F | D |
| Finish Pos | D | D |
| Dirt Speed | C | A |
| Turf Speed | A | A |
| Distance Speed | B | B |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | B |
| 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 | C | D |
| 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 | A | B |
| 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 | D | D |
| 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) Dropping in class today ($15,000 → $10,000). (2) Hot trainer - high ITM rate (45%). (3) Hot jockey — high ITM rate (38%). (4) In the money in last 3 consecutive starts. (5) Closer/presser in a race with pace pressure — ideal race setup for late runners. (6) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip. (7) Dropping in class ($10,000 vs last $15,000) after a 38-day freshening — trainer setup-for-win angle. (8) Had documented trouble last race (codes: ['B', 'D', 'F', 'L', 'O', 'T', 'U']) yet still finished 3rd — a clean trip today sets up a form reversal. (9) Averages 68.0 speed pts in today's distance/surface configuration vs 62.5 in other configs (8 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Has not raced in 38 days. (2) Trip note from last race: 3w; bid; flattened out. (3) Consistently breaks behind post position (3 of last 5 starts). (4) Last race was career-best speed (75) — bounce risk after peak effort. (5) First start at SRP — never raced here before (last seen at: TUP).
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: 64 (3/6) Mod4(Form): 94 (2/6) Win Prob: 63.1% Value Score: 3.17 ★ ML: 3.00 (2/1) Overlay %: -3.11 Fair Odds: 4.96 (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 | A | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | C |
| Early Pace | B | C |
| Mid Pace | A | B |
| Late Pace | C | C |
| Finish Pos | C | D |
| Dirt Speed | B | C |
| Turf Speed | A | C |
| Distance Speed | C | C |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | B | C |
| 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 | B |
| Sprint FPS | C | C |
| Route FPS | C | B |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | B | C |
| 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 | 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) Hot trainer - high ITM rate (50%). (2) Big last-race effort (74) — 27 pts above recent average. (3) Early pace significantly above field median (E1: 87 vs field 82). (4) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip. (5) Returning from 40-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (6) Trainer 'MORALES DANNY' has 3 horses in today's card all showing last-race improvement — barn appears sharp right now. (7) Had documented trouble last race (codes: ['D', 'L', 'O', 'T']) yet still finished 1st — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 40 days. (2) Rising in class today ($5,000 → $10,000). (3) Was claimed from its most recent race - new connections. (4) Consider there will be likely pace pressure in this race - multiple E types entered. (5) Speed average (54) well below field median (62). (6) Trip note from last race: Pace;geared down late. (7) Last race was career-best speed (74) — bounce risk after peak effort. (8) Stepping up to $10,000 — highest class level in last 10 starts (previous high: $5,000). (9) First start at SRP — never raced here before (last seen at: SUN).
Mod1(W): 85 (2/6) Mod2(W): 95 (2/6) Mod3(W): 94 (3/6) Mod1-LS: 66 (3/6) Mod2-LS: 96 (2/6) Mod3-LS: 56 (4/6) Mod4(Form): 100 (1/6) Win Prob: 61.4% Value Score: 2.7 ★ ML: 2.50 (3/2) Overlay %: -6.87 Fair Odds: 5.30 (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 | F | F |
| Early Pace | A | B |
| Mid Pace | C | C |
| Late Pace | F | D |
| Finish Pos | C | D |
| Dirt Speed | C | C |
| Turf Speed | C | D |
| Distance Speed | B | B |
| Trainer Effectiveness | A | A |
| 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 | A | B |
| Mid Pace | A | B |
| Late Pace | D | C |
| Sprint FPS | B | B |
| Route FPS | C | B |
| Trainer Effectiveness | A | A |
| 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 | F | F |
| Early Pace | A | A |
| 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) Speed average (68) well above field median (62). (2) Hot trainer - high ITM rate (54%). (3) Strong trainer/jockey combo - 3 wins from 8 starts (38%). (4) Hot jockey — high ITM rate (48%). (5) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip. (6) Career-best figure (74) buried in races 4–10 back — 12 pts above race median and 5 pts above recent form — market has forgotten the peak effort.
⚠ Concerns:(1) Rising in class today ($5,000 → $10,000). (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Trip note from last race: Traffic 2nd turn. (4) Has not won in last 10 starts despite career wins. (5) Rising in class ($5,000 → $10,000) after finishing 5 last out — double negative.
Mod1(W): 79 (3/6) Mod2(W): 88 (3/6) Mod3(W): 97 (2/6) Mod1-LS: 69 (2/6) Mod2-LS: 91 (3/6) Mod3-LS: 79 (2/6) Mod4(Form): 85 (3/6) Win Prob: 60.9% Value Score: 3.44 ★ ML: 3.50 (5/2) Overlay %: -1.73 Fair Odds: 5.26 (9/2) 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 | B | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | C |
| Early Pace | C | C |
| Mid Pace | A | C |
| Late Pace | B | B |
| Finish Pos | A | B |
| Dirt Speed | C | C |
| Turf Speed | C | D |
| Distance Speed | B | B |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | A |
| 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 | C | C |
| Mid Pace | C | C |
| Late Pace | C | C |
| Sprint FPS | A | B |
| Route FPS | A | A |
| Trainer Effectiveness | A | A |
| Jockey Effectiveness | A | A |
| 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 | A | C |
| Early Pace | C | 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) Returning from 54-day layoff with a recent workout. (2) Hot trainer - high ITM rate (50%). (3) Closer/presser in a race with pace pressure — ideal race setup for late runners. (4) Returning from 54-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (5) Trainer 'MORALES DANNY' has 3 horses in today's card all showing last-race improvement — barn appears sharp right now. (6) Had documented trouble last race (codes: ['B', 'D', 'O', 'S']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 54 days. (2) Rising in class today ($7,500 → $10,000). (3) Moving from a route to a sprint today. (4) Poor record at this distance (0 wins from 6 recent starts). (5) Trip note from last race: 2-3p;bid3/8;chase on. (6) First start at SRP — never raced here before (last seen at: SUN).
Mod1(W): 100 (1/7) Mod2(W): 100 (1/7) Mod3(W): 100 (1/7) Mod1-LS: 67 (4/7) Mod2-LS: 100 (1/7) Mod3-LS: 89 (2/7) Mod4(Form): 100 (1/7) Win Prob: 76.7% Value Score: 2.39 ★ ML: 1.20 (1/5) Overlay %: -17.30 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 | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | C | C |
| Early Pace | C | D |
| Mid Pace | D | C |
| Late Pace | B | A |
| Finish Pos | A | B |
| Dirt Speed | F | B |
| Turf Speed | B | B |
| Distance Speed | F | B |
| Trainer Effectiveness | A | A |
| 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 | B | B |
| Early Pace | D | D |
| Mid Pace | D | C |
| Late Pace | A | A |
| Sprint FPS | C | C |
| Route FPS | B | B |
| Trainer Effectiveness | A | A |
| 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 | C | C |
| Early Pace | C | 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) Big last-race effort (81) — 12 pts above recent average. (2) Returning from 34-day layoff with a bullet workout — trainer signaling extra readiness for today's spot. (3) Speed improved +13 pts then +6 pts in last 2 starts (62 → 75 → 81) — trainer is progressively building fitness. (4) Had documented trouble last race (codes: ['B', 'L', 'T']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 34 days. (2) Rising in class today ($7,500 → $10,000). (3) Was claimed from its most recent race - new connections. (4) Poor record at this distance (0 wins from 9 recent starts). (5) Trip note from last race: 4-3w;kept at bay lane. (6) Last race was career-best speed (81) — bounce risk after peak effort. (7) Has not won in last 10 starts despite career wins. (8) No workout in last 30 days despite 34 days since last race. (9) Stepping up to $10,000 — highest class level in last 10 starts (previous high: $7,500). (10) 0 wins from 10 starts on dirt in last 10 — repeated failure on today's surface. (11) Two consecutive 5+ pt speed jumps (62 → 75 → 81) and last race speed is well above career average (73) — high bounce risk after back-to-back peak efforts.
Mod1(W): 54 (4/7) Mod2(W): 63 (4/7) Mod3(W): 47 (4/7) Mod1-LS: 43 (7/7) Mod2-LS: 57 (4/7) Mod3-LS: 15 (6/7) Mod4(Form): 54 (4/7) Win Prob: 38.2% Value Score: 3.24 ★ ML: 5.00 (4/1) Overlay %: 1.53 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 | B | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | B | B |
| Early Pace | B | B |
| Mid Pace | B | B |
| Late Pace | D | B |
| Finish Pos | C | C |
| Dirt Speed | D | B |
| Turf Speed | C | B |
| Distance Speed | A | B |
| Trainer Effectiveness | F | D |
| Jockey Effectiveness | C | 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 | D | C |
| Early Pace | C | C |
| Mid Pace | B | B |
| Late Pace | D | B |
| Sprint FPS | B | B |
| Route FPS | B | A |
| Trainer Effectiveness | F | D |
| Jockey Effectiveness | C | 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 | B | C |
| 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) Returning from 48-day layoff with a recent workout. (2) In the money in last 4 consecutive starts. (3) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip. (4) Speed improved +4 pts then +7 pts in last 2 starts (74 → 78 → 85) — trainer is progressively building fitness. (5) Had documented trouble last race (codes: ['D', 'F', 'O', 'S', 'T', 'U']) yet still finished 2nd — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Has not raced in 48 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: 3-w; outfinished. (5) Last race was career-best speed (85) — bounce risk after peak effort.
Mod1(W): 78 (2/7) Mod2(W): 96 (2/7) Mod3(W): 77 (3/7) Mod1-LS: 76 (3/7) Mod2-LS: 94 (2/7) Mod3-LS: 61 (3/7) Mod4(Form): 78 (2/7) Win Prob: 65.3% Value Score: 3.69 ★ ML: 3.00 (2/1) Overlay %: -3.15 Fair Odds: 5.87 (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 | B |
| Early Pace | A | B |
| Mid Pace | A | B |
| Late Pace | C | B |
| Finish Pos | A | B |
| Dirt Speed | A | A |
| Turf Speed | D | D |
| Distance Speed | C | B |
| Trainer Effectiveness | B | C |
| Jockey Effectiveness | D | 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 | A | B |
| Early Pace | B | B |
| Mid Pace | A | A |
| Late Pace | B | A |
| Sprint FPS | A | A |
| Route FPS | A | A |
| Trainer Effectiveness | B | C |
| Jockey Effectiveness | D | 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 | B | B |
| 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) Dropping in class today ($20,000 → $10,000). (2) Hot jockey — high ITM rate (42%). (3) Late pace significantly above field median (LP: 87 vs field 80). (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 (105) — pedigree suggests main-track improvement is likely. (6) Had documented trouble last race (codes: ['D', 'F', 'L', 'V']) yet still finished 4th — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Moving from a route to a sprint today. (2) Switching from turf to dirt today. (3) Trip note from last race: 2-3p far;angled;imprvd. (4) Post 7 in a 8-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (5) First start at SRP — never raced here before (last seen at: TUP).
Mod1(W): 77 (3/7) Mod2(W): 84 (3/7) Mod3(W): 80 (2/7) Mod1-LS: 56 (5/7) Mod2-LS: 83 (3/7) Mod3-LS: 0 Mod4(Form): 66 (3/7) Win Prob: 55.6% Value Score: 3.93 ★ ML: 4.00 (3/1) Overlay %: -1.10 Fair Odds: 6.66 (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 | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | B |
| Early Pace | F | D |
| Mid Pace | F | D |
| Late Pace | A | A |
| Finish Pos | F | F |
| Dirt Speed | C | B |
| Turf Speed | A | A |
| Distance Speed | D | B |
| Trainer Effectiveness | C | D |
| 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 | B |
| Early Pace | F | D |
| Mid Pace | F | D |
| Late Pace | A | A |
| Sprint FPS | F | D |
| Route FPS | F | D |
| Trainer Effectiveness | C | D |
| 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 | A | B |
| 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) Closer/presser in a race with pace pressure — ideal race setup for late runners. (2) Has won at today's distance (990 yds) within the last 10 starts — proven ability at this trip. (3) Had documented trouble last race (codes: ['D', 'L', 'S']) yet still finished 4th — a clean trip today sets up a form reversal. (4) Averages 56.2 speed pts in today's distance/surface configuration vs 47.5 in other configs (8 qualifying starts) — returning to ideal setup.
⚠ Concerns:(1) Has not raced in 47 days. (2) Consider there will be likely pace pressure in this race - multiple E types entered. (3) Speed average (54) well below field median (64). (4) Trip note from last race: Inside;3p;mild gain. (5) Cold trainer - low ITM rate (6%). (6) Last race was career-best speed (62) — bounce risk after peak effort. (7) No workout in last 30 days despite 47 days since last race. (8) Speed figures are highly erratic over last 5 starts (σ = 17.2 pts: [62, 77, 85, 51, 44]) — unpredictable performer.
Mod1(W): 66 (4/7) Mod2(W): 62 (3/7) Mod3(W): 74 (3/7) Mod1-LS: 18 (7/7) Mod2-LS: 71 (3/7) Mod3-LS: 9 (7/7) Mod4(Form): 89 (3/7) Win Prob: 48.9% Value Score: 2.79 ★ ML: 3.50 (5/2) Overlay %: -5.08 Fair Odds: 7.02 (6/1) 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 | D | F |
| Early Pace | D | C |
| Mid Pace | D | D |
| Late Pace | D | D |
| Finish Pos | D | D |
| Dirt Speed | D | D |
| Turf Speed | C | D |
| Distance Speed | D | D |
| Trainer Effectiveness | F | F |
| 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 | A | B |
| Early Pace | D | D |
| Mid Pace | D | D |
| Late Pace | F | D |
| Sprint FPS | D | C |
| Route FPS | D | C |
| Trainer Effectiveness | F | F |
| 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 | F | D |
| Early Pace | D | 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) Speed average (69) well above field median (64). (2) Hot trainer - high ITM rate (44%). (3) Strong trainer/jockey combo - 4 wins from 7 starts (57%). (4) Hot jockey — high ITM rate (48%). (5) Won last 2 consecutive starts. (6) Has won at today's distance (990 yds) within the last 10 starts — proven ability at this trip. (7) Has won at SRP on dirt in the last 10 starts — proven at today's exact track/surface combo. (8) Career-best figure (86) buried in races 4–10 back — 22 pts above race median and 19 pts above recent form — market has forgotten the peak effort. (9) 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) Consider there will be likely pace pressure in this race - multiple E types entered. (2) Trip note from last race: Pressed;dueled;clear. (3) Speed figures are highly erratic over last 5 starts (σ = 8.8 pts: [66, 67, 65, 86, 68]) — unpredictable performer.
Mod1(W): 100 (1/7) Mod2(W): 100 (1/7) Mod3(W): 100 (1/7) Mod1-LS: 67 (2/7) Mod2-LS: 100 (1/7) Mod3-LS: 55 (2/7) Mod4(Form): 100 (1/7) Win Prob: 74.5% Value Score: 3.3 ★ ML: 2.50 (3/2) Overlay %: -9.23 Fair Odds: 6.50 (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 | A |
| Pace Trip Longshot | — | — |
| Connections Longshot | — | — |
| Situational Longshot | — | — |
| Speed | A | C |
| Early Pace | B | B |
| Mid Pace | B | B |
| Late Pace | A | B |
| Finish Pos | C | A |
| Dirt Speed | C | C |
| Turf Speed | C | D |
| Distance Speed | A | C |
| Trainer Effectiveness | B | 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 | D | C |
| Early Pace | B | B |
| Mid Pace | B | B |
| Late Pace | A | B |
| Sprint FPS | C | A |
| Route FPS | A | A |
| Trainer Effectiveness | B | 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 | B | 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) Hot trainer - high ITM rate (44%). (2) Career-best speed figure (62) recorded in last 1-2 starts — peaking form. (3) One gate workout in recent training — sharpness signal from the gate. (4) Has won at today's distance (990 yds) within the last 10 starts — proven ability at this trip. (5) Has won at SRP on dirt in the last 10 starts — proven at today's exact track/surface combo. (6) Had documented trouble last race (codes: ['D', 'S', 'T', 'V']) yet still finished 1st — 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) Limited experience at today's distance (1 start). (3) Unproven on dirt surface (1 start). (4) Trip note from last race: Vied inside;determined.
Mod1(W): 87 (2/7) Mod2(W): 70 (2/7) Mod3(W): 91 (2/7) Mod1-LS: 46 (4/7) Mod2-LS: 78 (2/7) Mod3-LS: 36 (3/7) Mod4(Form): 94 (2/7) Win Prob: 58.6% Value Score: 2.97 ★ ML: 3.00 (2/1) Overlay %: -5.79 Fair Odds: 6.17 (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 | D | D |
| Early Pace | C | C |
| Mid Pace | F | F |
| Late Pace | B | C |
| Finish Pos | A | A |
| Dirt Speed | D | D |
| Turf Speed | C | D |
| Distance Speed | B | C |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | D | 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 | D | D |
| Early Pace | D | C |
| Mid Pace | F | F |
| Late Pace | D | C |
| Sprint FPS | F | F |
| Route FPS | F | F |
| Trainer Effectiveness | B | B |
| Jockey Effectiveness | D | 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 | D |
| 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) Big last-race effort (81) — 16 pts above recent average. (2) In the money in last 6 consecutive starts. (3) Fourth race back from a 90-day layoff — often the peak fitness race. (4) Has won at today's distance (990 yds) within the last 10 starts — proven ability at this trip. (5) Speed improved +6 pts then +18 pts in last 2 starts (57 → 63 → 81) — trainer is progressively building fitness. (6) Trainer 'TSOSIE TERRILL' 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', 'F', 'O', 'S', 'T']) 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) Speed average (52) well below field median (64). (3) Trip note from last race: 3w; finished strong. (4) Consistently breaks behind post position (3 of last 5 starts). (5) Last race was career-best speed (81) — bounce risk after peak effort. (6) No workout in last 30 days despite 29 days since last race. (7) Post 7 in a 8-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path. (8) Speed figures are highly erratic over last 5 starts (σ = 11.4 pts: [81, 63, 57, 74, 54]) — unpredictable performer. (9) Two consecutive 5+ pt speed jumps (57 → 63 → 81) and last race speed is well above career average (58) — high bounce risk after back-to-back peak efforts.
Mod1(W): 81 (3/7) Mod2(W): 54 (4/7) Mod3(W): 64 (5/7) Mod1-LS: 30 (6/7) Mod2-LS: 68 (4/7) Mod3-LS: 36 (4/7) Mod4(Form): 74 (4/7) Win Prob: 54.2% Value Score: 3.78 ★ ML: 4.50 (7/2) Overlay %: 6.27 Fair Odds: 3.85 (3/1) 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 | F | F |
| Early Pace | D | C |
| Mid Pace | D | D |
| Late Pace | F | D |
| Finish Pos | A | A |
| Dirt Speed | F | D |
| Turf Speed | C | D |
| Distance Speed | C | C |
| Trainer Effectiveness | D | D |
| 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 | B | C |
| Early Pace | B | B |
| Mid Pace | D | C |
| Late Pace | D | D |
| Sprint FPS | A | A |
| Route FPS | B | A |
| Trainer Effectiveness | D | D |
| 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 | A | A |
| Early Pace | C | B |
| 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) Dropping in class today ($7,500 → $5,000). (2) Hot trainer - high ITM rate (47%). (3) Closer/presser in a race with pace pressure — ideal race setup for late runners. (4) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip.
⚠ Concerns:(1) Trip note from last race: Gain 4-5w;needed more.
Mod1(W): 81 (3/9) Mod2(W): 66 (3/9) Mod3(W): 83 (3/9) Mod1-LS: 23 (9/9) Mod2-LS: 67 (3/9) Mod3-LS: 76 (4/9) Mod4(Form): 67 (3/9) Win Prob: 48.2% Value Score: 3.72 ★ ML: 5.00 (4/1) Overlay %: -2.50 Fair Odds: 8.56 (8/1) 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 | C |
| Early Pace | B | C |
| Mid Pace | B | C |
| Late Pace | B | B |
| Finish Pos | A | B |
| Dirt Speed | F | C |
| Turf Speed | D | D |
| Distance Speed | C | C |
| Trainer Effectiveness | A | B |
| Jockey Effectiveness | B | 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 | A | C |
| Early Pace | B | C |
| Mid Pace | C | C |
| Late Pace | A | B |
| Sprint FPS | C | C |
| Route FPS | D | B |
| Trainer Effectiveness | A | B |
| Jockey Effectiveness | B | 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 | A | D |
| 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) Dropping in class today ($7,500 → $5,000). (2) Hot trainer - high ITM rate (45%). (3) Hot jockey — high ITM rate (42%). (4) Early pace significantly above field median (E1: 88 vs field 81). (5) Fourth race back from a 56-day layoff — often the peak fitness race. (6) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip.
⚠ Concerns:(1) Consider there will be likely pace pressure in this race - multiple E types entered. (2) Trip note from last race: Stp slw;stdy into turn. (3) Consistently breaks behind post position (3 of last 5 starts). (4) Outside post (9) in a large field of 10 horses. (5) Post 9 in a 10-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path.
Mod1(W): 98 (2/9) Mod2(W): 86 (2/9) Mod3(W): 100 (1/9) Mod1-LS: 54 (6/9) Mod2-LS: 92 (2/9) Mod3-LS: 100 (1/9) Mod4(Form): 83 (2/9) Win Prob: 69.6% Value Score: 4.47 ★ ML: 4.00 (3/1) Overlay %: -4.73 Fair Odds: 8.24 (7/1) 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 | D |
| Early Pace | A | B |
| Mid Pace | A | B |
| Late Pace | D | D |
| Finish Pos | A | C |
| Dirt Speed | D | C |
| Turf Speed | D | D |
| Distance Speed | D | C |
| Trainer Effectiveness | A | 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 | D | D |
| Early Pace | A | B |
| Mid Pace | A | A |
| Late Pace | D | D |
| Sprint FPS | B | A |
| Route FPS | C | A |
| Trainer Effectiveness | A | 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 | D |
| 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) Dropping in class today ($7,500 → $5,000). (2) Hot jockey — high ITM rate (39%). (3) Late pace significantly above field median (LP: 83 vs field 74). (4) Closer/presser in a race with pace pressure — ideal race setup for late runners. (5) Strong speed 2 back (71), modest dip last out (66) — form reversal angle, ready to bounce back to top form. (6) Has won at today's distance (1430 yds) within the last 10 starts — proven ability at this trip. (7) Has won at SRP 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', 'T', 'V']) yet still finished 1st — a clean trip today sets up a form reversal.
⚠ Concerns:(1) Trip note from last race: Settled; 4w; driving. (2) Outside post (10) in a large field of 10 horses. (3) Post 10 in a 10-horse dirt sprint — wide draw forces extra ground and a difficult first-turn path.
Mod1(W): 100 (1/9) Mod2(W): 100 (1/9) Mod3(W): 94 (2/9) Mod1-LS: 38 (8/9) Mod2-LS: 100 (1/9) Mod3-LS: 77 (3/9) Mod4(Form): 100 (1/9) Win Prob: 57.6% Value Score: 2.96 ★ ML: 3.00 (2/1) Overlay %: -8.30 Fair Odds: 7.97 (7/1) 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 | B | C |
| Early Pace | F | D |
| Mid Pace | D | D |
| Late Pace | A | A |
| Finish Pos | A | C |
| Dirt Speed | C | B |
| Turf Speed | D | D |
| Distance Speed | C | C |
| Trainer Effectiveness | C | D |
| 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 | C |
| Early Pace | F | F |
| Mid Pace | F | D |
| Late Pace | A | A |
| Sprint FPS | D | C |
| Route FPS | D | B |
| Trainer Effectiveness | C | D |
| 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 | D |
| Early Pace | F | D |
| Mid Pace | F | D |
| Late Pace | C | C |
TL;DR
Toggle
Get the full Handicapper Report, AI picks, expert analysis, and more with a Pick Pony subscription!
SunRay Park — May 9, 2026 — Quick Reference Card
Fast track expected throughout the card. Inside posts favored in sprints; stalkers with tactical speed best positioned in routes. Twelve-horse field in Race 4 makes outside posts problematic.
Race 1 — 990f | Md 7500 | 3:15 PM
Delightful Reserve (8) is the top pick at 2-1, offering the best closing chance if the early pace is contested. Ringo (4) at 3-1 is the main speed threat and most likely to upset if he gets loose on the front end. Nine Lives Elmer (1) from the rail is a fair show option at 4-1.
Race 2 — 1430f | Md 7500 | 3:40 PM
Attila Style (5) is the lone single at 2-1 in a wide-open maiden route and is the horse to build around in all exotics. Pleasin N Teasin (6) and Emotional Runaway (9) are both live at 4-1 and deserve coverage underneath. Michiga (3) at 8-1 is the best-priced secondary option if you want a value play in trifectas.
Race 3 — 990f | Clm 7500n2l | 4:05 PM
Hotshot Luk (5) at 3-1 is the top pick with the tactical speed to control or press the pace. Bonified Wildcat (6) at 4-1 is the main rival and a likely exacta partner. Runaway Goddess (3) at 8-1 represents solid upside value if her barn is pointing for a top effort.
Race 4 — 990f | Md 12500 | 4:30 PM
Tinaja (10) at 3-1 gets the nod based on trainer-jockey connectivity despite the wide post draw. Twist 'n Sport (3) at 4-1 is the strongest alternative with a clean inside draw, and Low Rollin (1) at 4-1 from the rail is dangerous if he breaks cleanly. Silver Twilight (6) at 6-1 and Charlie Thyme (8) at 8-1 are the most workable mid-price inclusions in trifectas.
Race 5 — 990f | Clm 7500b | 4:55 PM
Shell Game (8) at 3-1 is the top choice to benefit if Lone Mountain Girl (3) and Marksalot (6) fight for the early lead. Lone Mountain Girl (3) at 4-1 and Marksalot (6) at 4-1 are both legitimate win threats and necessary exacta coverage. La Vikina (9) at 6-1 is the best-priced longshot worth including in trifecta tickets.
Race 6 — 1430f | Clm 7500b | 5:20 PM
Brandyn (4) at 2-1 is the strongest single of the afternoon and a legitimate Pick 5 anchor. Scratchy Apache (1) at 3-1 is the most credible challenger and a necessary exacta opponent. Bettor Trip Nick (8) at 4-1 and Holland (6) at 4-1 round out the realistic trifecta coverage.
Race 7 — 1430f | Clm 10000n3l | 5:45 PM
Roki (3) at 2-1 is ideally placed to stalk and run down Drum Bunny (1) if the front-runner sets honest fractions. Drum Bunny (1) at 3-1 is a genuine wire-to-wire threat with the rail and a top rider. Truckin (7) at 4-1 is the most interesting live longshot and worth using as an alternate in the Pick 5.
Race 8 — 1430f | Clm 10000b | 6:10 PM
Ten Figures (2) at even money is the single of the day and the clearest class standout on the card. Discreet Mob (6) at 3-1 is the most logical closer and best exacta partner. I Am Freaky Fast (7) at 4-1 and Ham Sandwich (4) at 5-1 are the best trifecta fill options.
Race 9 — 990f | Alw 26780n2l | 6:35 PM
Albertus (4) at 2-1 is the feature race single, anchored by the father-son trainer-jockey angle in the day's richest event. Got No Bull (6) at 3-1 from the same barn cannot be dismissed and makes the same-trainer exacta an intriguing bet. Sunshine Lute (1) and Tracey's Kitchen (7) at 4-1 are both legitimate and required in trifecta coverage.
Race 10 — 1430f | Clm 5000b | 7:00 PM
John John (10) at 3-1 is the top selection in the finale with a credible pilot navigating the outside post. Held For Ransom (9) at 4-1 is the primary danger as a patient stalker with a skilled route rider. Be A Pro (6) at 5-1 for the meet's leading trainer is the best value play on the board to close the card.
Before wagering, check the Latest Race Scratches, Changes, and Conditions post for any last-minute scratches or race changes.
Unlock the full Handicapper Report and enjoy all Pick Pony membership perks!
✓ Positives:(1) Career-best speed figure (62) recorded in last 1-2 starts — peaking form. (2) Closer/presser in a race with pace pressure — ideal race setup for late runners. (3) Fourth race back from a 57-day layoff — often the peak fitness race. (4) Career-best figure (83) buried in races 4–10 back — 28 pts above race median and 21 pts above recent form — market has forgotten the peak effort. (5) Averages 57.4 speed pts in today's distance/surface configuration vs 49.7 in other configs (7 qualifying starts) — returning to ideal setup.