TrackSmart AI: Cumulative Performance Report - NYRA & Regional Tracks
Reporting Period: December 26, 2025 – June 21, 2026
Track: Belmont at the Big A (BAQ) / Finger Lakes (FL) / Aqueduct (AQU) / Laurel Park (LRL) / Santa Anita Park (SA) / Penn National (PEN) / Saratoga Harness (SARH) / Woodbine (WO) / Saratoga (SAR)
- Executive Summary: June 21 Update
- Volume Expansion: The tracking dataset has grown to 1036 total races with the addition of 50 races run across Finger Lakes and Belmont at the Big A from June 15 through June
- Strike Rate Resilience: The cumulative Top 4 Strike Rate held perfectly steady at 77.6% (804 for 1036). The AI model turned in a spectacular week, highlighted by 87.5% hit rates at Belmont at the Big A on both June 18 and June 21, and an impressive 6-win top-choice performance on June 20.
- Value Normalization: The Average Payout for AI hits rebounded slightly to ~$7.73 (up minimally from ~$7.70). Heavy value identification anchored the week, catching substantial payouts like Sir Kartrite ($31.18) on June 16, Kunshan Bridge ($25.94) on June 20, and Smiling Rosie ($20.54) on June
- System Integrity and Updates: The automated scratch adjustment protocol was extensively validated this Moving up Alternate selections cleanly absorbed heavy scratch volume on the June 18, 19, and 21 cards, actively securing top-tier hits and keeping multi-race tickets alive with no drop in top-end confidence.
- Daily Performance Breakdown
|
Date |
Track |
Top 4 Strike Rate |
Total Races |
1st Pick |
2nd Pick |
3rd Pick |
4th Pick |
Avg Payout (AI Hits) |
|
Prev. Totals |
MULTI |
77.6% |
986 |
293 |
195 |
181 |
96 |
~$7.70 |
|
June 15 |
FL |
75.0% |
8 |
4 |
2 |
0 |
0 |
$5.56 |
|
June 16 |
FL |
75.0% |
8 |
1 |
2 |
3 |
0 |
$9.70 |
|
June 18 |
BAQ |
87.5% |
8 |
4 |
2 |
0 |
1 |
$7.58 |
|
June 19 |
BAQ |
75.0% |
8 |
1 |
1 |
3 |
1 |
$5.51 |
|
June 20 |
BAQ |
70.0% |
10 |
6 |
0 |
0 |
1 |
$11.38 |
|
June 21 |
BAQ |
87.5% |
8 |
2 |
3 |
1 |
1 |
$9.51 |
|
NEW TOTALS |
MULTI |
77.6% |
1036 |
311 |
205 |
188 |
100 |
~$7.73 |
(Note: Prior totals reflect cumulative data up to June 14. Daily breakdowns from previous reports have been condensed into the Prev. Totals row. Live scratch protocols dynamically shifted runners up in rankings across multiple races this week, securing numerous top-tier hits.)
- Winner Distribution by Rank (Cumulative)
|
AI Rank Wins % of Trend Note Hits |
|||
|
Top Pick |
311 |
38.7% |
Pace Flow Precision: Continued dominance identifying undisputed inside speed and wire-to-wire profiles, specifically yielding massive returns with six top-choice winners on the June 20 BAQ card. |
|
2nd Selection |
205 |
25.5% |
Class Elevation & Adaptability: Remained highly consistent in finding pocket trips and logical stalkers that capitalized on front-end pressure, adapting well to scratch-based promotions. |
|
3rd Selection |
188 |
23.4% |
Alternate Protection: Reaped massive rewards catching off-the-pace sweepers and deep values, sniffing out favorable setups like ground-saving inside trips. |
|
4th Selection |
100 |
12.4% |
Rebounding Safety Net: Secured solid exotic value acting as reliable scratch survivors, stepping up accurately when logical chaos angles materialized, such as Smiling Rosie ($20.54). |
- Cumulative Statistics Summary
|
Metric Stat Description |
||
|
Overall Accuracy |
77.6% |
(804/1036 Races) The AI has successfully placed the winner in its Top 4 selections in 804 of the 1036 recorded races. |
|
Top 2 Accuracy |
49.8% |
(516/1036 Races) The primary or secondary choice remains highly reliable, winning in nearly half of all modeled races. |
|
Avg Payout |
~$7.73 |
The average payout trended upwards slightly, driven by massive mid-week hits like Sir Kartrite ($31.18) and a string of strong top-choice selections offsetting favorite-heavy results. |
- Aggregate Observations: June 15 - June 21 Insights
- Incredible Top-End Dominance: The AI engine delivered an incredibly sharp performance on June 20 at BAQ, securing six top-choice (1st) winners out of 10 races and returning highly generous overall payouts of $17.04,
$13.82, and $21.58 inside the top tier.
- Pace Projection & Track Bias Accuracy: The model expertly mapped race environments. It correctly isolated "Honest Pace" structures in turf routes and confidently predicted "Contested Duel" meltdowns (e.g., Race 5 at FL on June 15). The AI also successfully utilized track bias overlays ("E/P bias") to lock in rail/pressing
- Deep Alternate Values: The machine's alternate selection logic proved incredibly potent for identifying hidden value. By specifically flagging favorable pace dynamics and "ground-saving inside trips," the AI caught massive overlay winners like Smiling Rosie ($20.54) and Tapwrits Temper ($8.04).
- Chaos Immunity & Vulnerabilities: While the machine comfortably locked onto fair-value longshots, it proved vulnerable to extreme un-modeled Complete meltdowns and massive form reversals by horses like Bandmaster ($71.44) and Into the Light ($33.20) bypassed standard baseline metrics. The AI also operated completely blind to the tote board, missing heavily bet favorites (like Pencima and Probably Flattery) when it aggressively anticipated pace meltdowns that didn't materialize.
- Scratch Protocol Validation: Automated adjustment rules proved indispensable once again. Under heavy late scratch conditions across the week (particularly on June 18, 19, and 21), moving depth selections perfectly filled top-tier This logic successfully captured winners in the adjusted Top 4 every single time a scratch hit the top configurations.

