What a week it was for Pick Pony's AI engine! Across all three algorithms, our system analyzed 850 races, with 808 settled and 42 still pending — so the final numbers may look even better once those results come in. Each algorithm delivered rock-solid in-the-money rates hovering right around 57%, meaning our top pick finished win, place, or show in more than half of all settled races. Algo3 led the way in outright wins with a 26.2% win rate (212 wins), while Algo2 was right on its heels at 26.1% (211 wins) and Algo1 rounded out the trio at 25.5% (206 wins). On the exotic side, the algorithms combined for dozens of exacta and trifecta hits — including 53 boxed trifectas from Algo2 alone — giving bettors plenty of multi-race payoff opportunities throughout the week.
Standout Wins
The highlight reel this week is absolutely loaded with longshot glory. BUSTIN LOOSE at Mountaineer on June 9th was a consensus star across all three algorithms, rolling home at a jaw-dropping 15-1 morning line — exactly the kind of overlaid winner our AI is built to find. Algo1 deserves a special shoutout for nailing PRAETORIAN GUARD (10-1) at Parx on June 10th and OLYMPIC FLAME (10-1) at Prairie Meadows on June 14th, two double-digit shots that lesser models would have buried. Meanwhile, Algo2 scored with HAWIJA (8-1) at Evangeline Downs on June 12th and TAHINI (6-1) atساксony — demonstrating consistent value-finding across multiple circuit types. Algo3 had its own standout stretch, capping the week with wins from PERFECT SELINA (10-1), LEGAL HEIR (6-1), and JUST A TOUCH (6-1) across three different tracks on back-to-back days. Across all three algorithms, SHE'S ON FIRE (8-1), FREAKY NEEKS (6-1), and MOMENTUM FILES (6-1) each appeared as winning picks in multiple models simultaneously — a powerful signal of AI confidence that paid off beautifully.
Key Insights
This week's data tells a compelling story about where our AI is sharpest. The concentration of longshot wins — multiple double-digit morning line upsets across tracks like Mountaineer, Prairie Meadows, Wyoming Downs, and Parx — suggests our algorithms are particularly effective at identifying undervalued horses in spots where public money inflates the favorites. The cross-algorithm agreement on horses like BUSTIN LOOSE, PERFECT SELINA, SHE'S ON FIRE, FREAKY NEEKS, and MOMENTUM FILES (all three models picking them, all winners) is a strong validation that our ensemble approach is functioning exactly as designed. When all three algorithms agree, bettors should take note — that convergence has proven to be one of the most reliable signals in the system. With 42 races still pending settlement, there's a real chance several of those results push our win and ITM totals even higher before next week's recap.
Looking Ahead
The algorithms are firing on all cylinders heading into the final stretch of the June meet calendar, and with dozens of races still pending from this week's card, the best numbers may not even be in yet. Keep an eye out for those cross-algorithm consensus picks — when Algo1, Algo2, and Algo3 all line up on the same horse, this week proved once again that's exactly where the value lives. Stay tuned, stay sharp, and let Pick Pony's AI do the heavy lifting! 🏇
Weekly Performance Summary
Algorithm Algo1 Winner
Pick Pony's AI Winner models rank every horse in each race using a weighted combination of speed figures, pace analysis, trainer/jockey statistics, track bias, and dozens of other handicapping factors. Each algorithm uses a different set of optimized weights to capture different angles on the same race data. Top Pick Wins measures how often the model's #1 ranked horse won the race outright. Places and Shows count 2nd and 3rd place finishes respectively. ITM (In The Money) is the combined total of Win + Place + Show. Rates are calculated against settled races only (pending results excluded). The Exotic Wager Hits table shows how often the model's top 3 picks finished in the correct order (Exacta/Trifecta) or in any order within the top positions (Boxed Exacta/Boxed Trifecta).
Metric
Count
Rate
Total Races
850
Top Pick Wins (1st)
210
26.0%
Top Pick Places (2nd)
159
19.7%
Top Pick Shows (3rd)
112
13.8%
Top Pick ITM
481
59.5%
Pending
41
Exotic Wager Hits (Algorithm Algo1 Winner)
Wager Type
Hits
Description
Exacta
57
Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta
55
Picks 1 & 2 both finished in top 2, reversed order
Trifecta
17
Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Picks 1 & 2 both finished in top 2, reversed order
Trifecta
14
Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta
60
Picks 1, 2 & 3 all finished in top 3, any order
Algorithm Algo3 Winner
Metric
Count
Rate
Total Races
850
Top Pick Wins (1st)
218
26.9%
Top Pick Places (2nd)
143
17.7%
Top Pick Shows (3rd)
114
14.1%
Top Pick ITM
475
58.7%
Pending
41
Exotic Wager Hits (Algorithm Algo3 Winner)
Wager Type
Hits
Description
Exacta
55
Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta
48
Picks 1 & 2 both finished in top 2, reversed order
Trifecta
19
Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta
58
Picks 1, 2 & 3 all finished in top 3, any order
Algorithm Algo1 Longshot
Longshot picks isolate races where the AI's top-ranked horse had morning-line odds of 8-1 or greater — horses the betting public considers unlikely to win. These are higher-risk, higher-reward selections where the model identified an edge that the public odds did not reflect. Because longshots win far less frequently by definition (typically 10-15% of races), win rates in this section are expected to be substantially lower than the winner models above. That is normal and by design — even a modest longshot win rate of 5-10% can be highly profitable because the payoffs are dramatically larger. A $2 win bet on an 8-1 longshot returns $18. Focus on ITM rate and exotic hits rather than raw win percentage when evaluating longshot model performance. The same Win/Place/Show/ITM and Exotic metrics apply as described above.
Picks 1 & 2 both finished in top 2, reversed order
Trifecta
0
Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta
0
Picks 1, 2 & 3 all finished in top 3, any order
Algorithm Algo2 Longshot
Metric
Count
Rate
Total Races
734
Top Pick Wins (1st)
34
4.8%
Top Pick Places (2nd)
62
8.8%
Top Pick Shows (3rd)
69
9.8%
Top Pick ITM
165
23.5%
Pending
32
Exotic Wager Hits (Algorithm Algo2 Longshot)
Wager Type
Hits
Description
Exacta
1
Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta
2
Picks 1 & 2 both finished in top 2, reversed order
Trifecta
0
Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta
0
Picks 1, 2 & 3 all finished in top 3, any order
Algorithm Algo3 Longshot
Metric
Count
Rate
Total Races
734
Top Pick Wins (1st)
31
4.4%
Top Pick Places (2nd)
59
8.4%
Top Pick Shows (3rd)
71
10.1%
Top Pick ITM
161
22.9%
Pending
32
Exotic Wager Hits (Algorithm Algo3 Longshot)
Wager Type
Hits
Description
Exacta
2
Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta
0
Picks 1 & 2 both finished in top 2, reversed order
Trifecta
0
Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta
1
Picks 1, 2 & 3 all finished in top 3, any order
Longshot Betting Strategy Simulator
Each strategy below replays the past 60 days of AI longshot picks as actual $2 mutuel bets and reports the realised return. A longer window than the rest of this report is used here on purpose: longshots are rare and extremely high-variance, so a single week's results are dominated by luck — only over a larger sample do the calibrated edge strategies separate from simply betting every longshot. Bets are deduplicated by (track, race, horse) so a horse picked by all three algorithms generates one bet, not three. The 2+ algos agree strategies capture races where two or more algorithms converged on the same longshot. Edge strategies use a calibrated win probability (from the longshot meta-learner) and bet only when P(win) × decimal odds − 1 exceeds the listed threshold — these target overlays rather than long prices for their own sake. Hit% is the share of tickets that cashed any leg. Unique horse-race picks evaluated: 14632 (calibration data on 14632).
Strategy
Bets
Tickets Cashed
Stake
Payout
Profit
ROI
$2 WIN — all longshots
14632
733 (5.0%)
$29264.00
$18811.16
$-10452.84
-35.7%
$2 PLACE — all longshots
14632
1781 (12.2%)
$29264.00
$18434.12
$-10829.88
-37.0%
$2 SHOW — all longshots
14632
3223 (22.0%)
$29264.00
$19375.12
$-9888.88
-33.8%
$2 WIN + $2 PLACE
14632
1781 (12.2%)
$58528.00
$37245.28
$-21282.72
-36.4%
$2 WIN — ML ≥ 15/1
7992
301 (3.8%)
$15984.00
$9404.18
$-6579.82
-41.2%
$2 WIN — ML ≥ 20/1
4527
122 (2.7%)
$9054.00
$4678.14
$-4375.86
-48.3%
$2 WIN — field ≥ 8
9207
406 (4.4%)
$18414.00
$11847.30
$-6566.70
-35.7%
$2 WIN — 2+ algos agree
14632
733 (5.0%)
$29264.00
$18811.16
$-10452.84
-35.7%
$2 WIN — 3 algos unanimous
14632
733 (5.0%)
$29264.00
$18811.16
$-10452.84
-35.7%
$2 WIN — field ≥ 8 AND 2+ algos
9207
406 (4.4%)
$18414.00
$11847.30
$-6566.70
-35.7%
$2 WIN — edge ≥ 5%
3603
289 (8.0%)
$7206.00
$6790.86
$-415.14
-5.8%
$2 WIN — edge ≥ 10%
3192
273 (8.6%)
$6384.00
$6361.64
$-22.36
-0.4%
$2 WIN — edge ≥ 20%
2704
232 (8.6%)
$5408.00
$5442.94
$+34.94
+0.6%
$2 WIN — edge ≥ 30%
2552
222 (8.7%)
$5104.00
$5312.50
$+208.50
+4.1%
$2 WIN — edge ≥ 40%
1822
201 (11.0%)
$3644.00
$4407.40
$+763.40
+20.9%
$2 WIN — edge ≥ 50%
1626
172 (10.6%)
$3252.00
$3860.38
$+608.38
+18.7%
$2 WIN — edge ≥ 60%
1451
158 (10.9%)
$2902.00
$3460.10
$+558.10
+19.2%
$2 WIN — edge ≥ 70%
1305
142 (10.9%)
$2610.00
$3243.44
$+633.44
+24.3%
$2 WIN — edge ≥ 80%
1232
133 (10.8%)
$2464.00
$3003.72
$+539.72
+21.9%
$2 WIN — edge ≥ 90%
1014
105 (10.4%)
$2028.00
$2503.84
$+475.84
+23.5%
$2 WIN — edge ≥ 100%
900
98 (10.9%)
$1800.00
$2374.84
$+574.84
+31.9%
$2 WIN — edge ≥ 10% AND field ≥ 8
1749
127 (7.3%)
$3498.00
$3587.50
$+89.50
+2.6%
$2 WIN — edge ≥ 10% AND 2+ algos
3192
273 (8.6%)
$6384.00
$6361.64
$-22.36
-0.4%
Consensus Expert Picks
Consensus Expert Picks are derived from multiple independent handicapping sources. Each source submits their top picks per race, and the consensus ranking is built by scoring each horse: 4 points for a 1st-place pick, 3 for 2nd, 2 for 3rd, and 1 for 4th. The horse with the highest total score becomes the consensus top pick. Agreement % measures what share of experts included a horse in their picks — higher agreement signals stronger conviction across sources. The Win/Place/Show/ITM and Exotic stats below measure how the consensus top pick actually performed on race day.
Picks 1 & 2 both finished in top 2, reversed order
Trifecta
18
Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta
34
Picks 1, 2 & 3 all finished in top 3, any order
Performance by Breed
Top-pick win rates vary dramatically by breed. Thoroughbred (TB) racing is the most form-driven and predictable, while Quarter Horse (QH) and Arabian (AR) sprints are decided in a few hundred yards and are far more chaotic — they naturally produce lower win rates. Because the summary above blends all breeds together, this table separates them so each breed's true performance is visible. W/P/S are wins, places (2nd), and shows (3rd), with the percentage of settled races in parentheses. ITM is the In-The-Money total (Win + Place + Show). EX/BEX/TRI/BTRI are exacta, boxed-exacta, trifecta, and boxed-trifecta hits on the top picks.
Thoroughbred
Source
Races
W
P
S
ITM
EX
BEX
TRI
BTRI
Algo 1 Winner
736
178 (25%)
144 (20%)
99 (14%)
421 (60%)
49
50
15
50
Algo 2 Winner
736
195 (28%)
134 (19%)
94 (13%)
423 (60%)
52
44
11
55
Algo 3 Winner
736
197 (28%)
124 (18%)
98 (14%)
419 (59%)
50
41
18
51
Algo 1 Longshot
636
36 (6%)
54 (9%)
60 (10%)
150 (25%)
2
1
0
0
Algo 2 Longshot
636
30 (5%)
54 (9%)
58 (10%)
142 (23%)
1
1
0
0
Algo 3 Longshot
636
26 (4%)
51 (8%)
62 (10%)
139 (23%)
2
0
0
1
Quarter Horse
Source
Races
W
P
S
ITM
EX
BEX
TRI
BTRI
Algo 1 Winner
109
30 (31%)
13 (13%)
13 (13%)
56 (57%)
8
5
2
11
Algo 2 Winner
109
21 (21%)
19 (19%)
11 (11%)
51 (52%)
9
4
3
5
Algo 3 Winner
109
21 (21%)
18 (18%)
15 (15%)
54 (55%)
5
7
1
7
Algo 1 Longshot
94
4 (4%)
9 (10%)
10 (11%)
23 (26%)
0
1
0
0
Algo 2 Longshot
94
4 (4%)
8 (9%)
10 (11%)
22 (24%)
0
1
0
0
Algo 3 Longshot
94
5 (6%)
8 (9%)
8 (9%)
21 (23%)
0
0
0
0
Mixed
Source
Races
W
P
S
ITM
EX
BEX
TRI
BTRI
Algo 1 Winner
5
2 (40%)
2 (40%)
0 (0%)
4 (80%)
0
0
0
0
Algo 2 Winner
5
0 (0%)
1 (20%)
1 (20%)
2 (40%)
0
0
0
0
Algo 3 Winner
5
0 (0%)
1 (20%)
1 (20%)
2 (40%)
0
0
0
0
Algo 1 Longshot
4
0 (0%)
0 (0%)
1 (25%)
1 (25%)
0
0
0
0
Algo 2 Longshot
4
0 (0%)
0 (0%)
1 (25%)
1 (25%)
0
0
0
0
Algo 3 Longshot
4
0 (0%)
0 (0%)
1 (25%)
1 (25%)
0
0
0
0
Performance by Track
The tables below break down each pick source's performance at individual tracks. W/P/S show the number of wins, places (2nd), and shows (3rd) with the percentage of settled races in parentheses. ITM is the combined In The Money total (Win + Place + Show). EX (Exacta) counts races where the top 2 picks finished 1st and 2nd in exact order. BEX (Boxed Exacta) counts races where the top 2 picks both finished in the top 2 in either order. TRI (Trifecta) and BTRI (Boxed Trifecta) apply the same logic to the top 3 picks finishing in the top 3 positions. Each algorithm (Algo 1, 2, 3) uses different optimized weights, so their performance varies by track — comparing across algorithms at a specific track helps identify which model is strongest for that venue.
