What a week to be a Pick Pony subscriber! Across all of our AI algorithms, the system covered an impressive 734 races through the Algo1, Algo2, and Algo3 families, with the specialized Ai Exacta and Ensemble models adding hundreds more. When the dust settled, our algorithms were firing on all cylinders — posting top-pick win rates ranging from 30.3% up to an outstanding 37.3% for the Ensemble model. To put that in perspective, the morning-line favorite — the so-called “chalk” that the entire industry leans on — won just 36.6% of the same benchmark races this week. Our Ensemble algorithm beat that baseline outright, and every single one of our models ran neck-and-neck with or near it while spanning a far broader and more diverse pool of races. ITM (In The Money) rates were equally impressive, with most algorithms landing between 64.8% and 67.5%, meaning our top picks finished in the top three nearly two out of every three times. It's also worth noting that dozens of races across all models are still listed as pending settlement, so several of those numbers have room to grow even further before the week is fully closed out.
Standout Wins
The highlight reel this week is absolutely worth celebrating. The Ai Exacta model had a spectacular August 16th, rattling off eight top-pick winners in a single day — including NASTY HABIT (5-1) at DMR R9, BRAYBRAY (3-1) at SWF, and HOMEAWAYFROMHOME (3-1) at ELP, proving the model's ability to identify winners across multiple tracks simultaneously. The Ensemble algorithm — our most selective and consensus-driven model — continued to shine with a standout card on August 15th, hitting CAUSEWAY BENNY (5-1), IMPERIAL SPY (4-1), STEAK FRIES (4-1), CADENZA (4-1), and more across EVD, PRX, DMR, and SAR in the same afternoon. On the longshot front, the Algo1 and Algo2 families delivered some serious value, with SPECIAL COLLETTE going off at 10-1 at TDN, GREYHOUND STATION paying at 10-1 at MNR, and MODONDAY (8-1) at GPX — a horse that appeared across multiple algorithms simultaneously, a strong signal of genuine AI conviction. When our models agree, it shows, and MODONDAY delivered.
Key Insights
A few clear themes emerged from this week's data. First, multi-track Saturday coverage continues to be a sweet spot for our AI — August 16th was particularly strong, with wins spread across DMR, ALB, ELP, SWF, EMD, CBY, MTH, and CNL all in a single day, demonstrating the system's ability to process and rank horses across the full national card without losing edge. Second, the longshot identification was exceptional this week. Hits at 8-1 and 10-1 aren't lucky flukes — they reflect the AI's ability to find horses whose true probability of winning is meaningfully higher than what the public betting pools reflect, which is exactly the value proposition Pick Pony is built on. Third, the exotic hit counts were robust across the board — Algo1 alone connected on 58 straight exactas, 42 boxed trifectas, and 18 straight trifectas, giving players who play beyond win bets plenty of ammunition for strong multi-race and multi-horse payouts. Those exotic structures, layered on top of solid win-rate performance, represent where the real bankroll growth happens week over week.
Looking Ahead
With dozens of races still pending final settlement, this week's numbers could look even better by the time the full results come in — so keep an eye on your dashboard for updates. Next week brings another full national card, and with our Ensemble model running above the chalk baseline and the longshot radar clearly locked in, there's every reason to stay engaged and trust the picks. Let's keep the momentum going! 🏇
Weekly Performance Summary
Ai Exacta 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).
Picks 1 & 2 both finished in top 2, reversed order
Trifecta
13
Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta
41
Picks 1, 2 & 3 all finished in top 3, any order
Algorithm Algo3 Am Winner
Metric
Count
Rate
Total Races
734
Top Pick Wins (1st)
169
30.5%
Top Pick Places (2nd)
99
17.9%
Top Pick Shows (3rd)
95
17.1%
Top Pick ITM
363
65.5%
Pending
114
Exotic Wager Hits (Algorithm Algo3 Am Winner)
Wager Type
Hits
Description
Exacta
50
Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta
36
Picks 1 & 2 both finished in top 2, reversed order
Trifecta
13
Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta
41
Picks 1, 2 & 3 all finished in top 3, any order
Algorithm Ensemble Winner
Metric
Count
Rate
Total Races
384
Top Pick Wins (1st)
100
37.3%
Top Pick Places (2nd)
48
17.9%
Top Pick Shows (3rd)
33
12.3%
Top Pick ITM
181
67.5%
Pending
89
Exotic Wager Hits (Algorithm Ensemble Winner)
Wager Type
Hits
Description
Exacta
30
Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta
17
Picks 1 & 2 both finished in top 2, reversed order
Trifecta
8
Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta
22
Picks 1, 2 & 3 all finished in top 3, any order
AI Longshot Picks
Longshot picks are individual horses flagged at publication time: their morning-line odds were 8-1 or greater — prices the betting public considers unlikely to win — and the model's calibrated win probability said the price overpaid. Unlike the winner models above, a longshot is not a race's top-ranked horse, so these tables count selections, not races: every flagged horse is one bet, graded on its own finish, and a single race can contribute more than one. (For the same reason there is no exotic-hits table here — an exacta or trifecta needs a ranked 1-2-3 ticket, which a set of longshot flags does not define.) There is also one longshot table rather than one per algorithm: the flag depends only on the horse's price and its calibrated edge, never on where an algorithm ranked it, so all three models publish exactly the same longshot list. Because longshots win far less frequently by definition, 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 on the realised ROI in the Longshot Betting Strategy Simulator below rather than on raw win percentage when evaluating longshot model performance.
Metric
Count
Rate
Longshot Selections
472
Races Covered
324
Wins (1st)
27
7.8%
Places (2nd)
40
11.6%
Shows (3rd)
42
12.2%
ITM
109
31.7%
Pending
50
Benchmark: The Morning-Line Favorite
The simplest possible strategy is to always bet the morning-line favorite — the “chalk.” This table shows how that baseline performed across the same thoroughbred races this week, so you can judge the AI's win rates against what the public's top choice delivered. Beating the chalk consistently is the real test of any handicapping model.
Metric
Count
Rate
Settled Races
535
Favorite Wins (1st)
196
36.6%
Favorite Places (2nd)
102
19.1%
Favorite Shows (3rd)
80
15.0%
Favorite ITM
378
70.7%
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.
Metric
Count
Rate
Total Races
641
Top Pick Wins (1st)
156
33.1%
Top Pick Places (2nd)
96
20.4%
Top Pick Shows (3rd)
80
17.0%
Top Pick ITM
332
70.5%
Pending
170
Exotic Wager Hits (Consensus Top 3 Picks)
Wager Type
Hits
Description
Exacta
39
Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta
31
Picks 1 & 2 both finished in top 2, reversed order
Trifecta
12
Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta
46
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. Longshot rows count individual flagged selections rather than races (a race can contribute more than one), and show dashes for the exotic columns because those wagers need a ranked 1-2-3 ticket.
Thoroughbred
Source
Races
W
P
S
ITM
EX
BEX
TRI
BTRI
Algo 1 Winner
734
185 (33%)
94 (17%)
83 (15%)
362 (65%)
56
26
16
42
Algo 2 Winner
734
176 (32%)
98 (18%)
93 (17%)
367 (66%)
53
34
15
42
Algo 3 Winner
734
170 (31%)
99 (18%)
95 (17%)
364 (65%)
50
36
13
41
AI Longshot
472
27 (8%)
40 (12%)
42 (12%)
109 (32%)
—
—
—
—
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. Longshot rows count individual flagged selections rather than races (a race can contribute more than one) and show dashes in the exotic columns, because those wagers need a ranked 1-2-3 ticket that a per-horse longshot flag does not define. 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. The ML Favorite (chalk) row shows how the morning-line favorite performed in that track's thoroughbred races — the baseline any pick source needs to beat to be adding value at that venue.
