TrackSmart AI: Cumulative Performance Report - NYRA & Regional Tracks Reporting Period: December 26, 2025 – July 12, 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)

  1. Executive Summary: July 12 Update
  • Volume Expansion: The tracking dataset has grown to 1199 total races with the addition of 62 races run across Finger Lakes and Saratoga from July 6 through July
  • Strike Rate Resilience: The cumulative Top 4 Strike Rate shifted slightly but maintained a highly consistent 77.4% (928 for 1199). The AI model delivered an exceptional early week at Finger Lakes, highlighted by a flawless 100% Top 4 hit rate on July 8 (8 for 8), while managing extreme variance and chaos results during Saratoga's highly competitive late-week cards.
  • Value Normalization: The Average Payout for AI hits remained perfectly stabilized at ~$7.79. Deep value identification continued to anchor the week, capturing substantial payouts like Malibu Smart ($28.20) on July 12, After Taxes (IRE) ($18.72) on July 9, Love Thyself ($14.00) on July 8, and Movin' On Up ($12.62) on July
  • System Integrity and Updates: The automated scratch adjustment protocol continued to be extremely lucrative. Field alternates filling vacated positions seamlessly absorbed scratch volume, directly bumping up alternates into winning positions and securing payouts like Movin' On Up ($12.62) on July 11, Karey ($9.44) on July 9, and Carol Said No ($5.20) on July 8 with no drop in top-end confidence.
  1. 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

 

77.9%

 

1137

 

342

 

230

 

205

 

109

 

~$7.81

July 6

FL

87.5%

8

5

2

0

0

$4.36

July 7

FL

85.7%

7

4

1

0

1

$6.53

July 8

FL

100.0%

8

2

3

3

0

$7.81

July 9

SAR

77.8%

9

3

3

1

0

$8.19

July 10

SAR

40.0%

10

0

0

4

0

$6.81

July 11

SAR

54.5%

11

2

2

1

1

$6.86

July 12

SAR

44.4%

9

1

1

0

2

$13.35

NEW TOTALS

 

MULTI

 

77.4%

 

1199

 

359

 

242

 

214

 

113

 

~$7.79

 

(Note: Prior totals reflect cumulative data up to July 5. 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.)

  1. Winner Distribution by Rank (Cumulative)

 

 

AI Rank

 

Wins

% of Hits

 

Trend Note

 

Top Pick

 

359

 

38.7%

Pace Flow Precision: Kept catching steady winners with solid pace projection. Successfully mapped out "Honest Paces" and fast dirt profiles (TSE1/TSE2 metrics), dominating outright at Finger Lakes early in the week.

2nd Selection

 

242

 

26.1%

Class Elevation & Adaptability: Remained a highly reliable choice, providing an excellent safety net during projected meltdowns and heavily capitalizing on scratch

 

 

 

 

 

promotions (e.g., Karey on July 9).

 

3rd Selection

 

214

 

23.1%

Alternate Protection: Consistently sniffing out favorable setups and deep values. Benefited immensely from class drops and "Trouble-Trip Rebound" angles as seen across Finger Lakes fields.

 

4th Selection

 

113

 

12.2%

Rebounding Safety Net: Capitalized heavily on chaos outcomes and automated scratch-bumping rules, stepping up to capture mid-to-high payouts like Movin' On Up ($12.62) and Malibu Smart ($28.20).

 

  1. Cumulative Statistics Summary

 

Metric         Stat         Description

Overall Accuracy

 

77.4%

(928/1199 Races) The AI has successfully placed the winner in its Top 4 selections in 928 of the 1199 recorded races.

Top 2 Accuracy

 

50.1%

(601/1199 Races) The primary or secondary choice remains highly reliable, winning in just over half of all modeled races.

Avg Payout

 

~$7.79

The average payout remained incredibly stabilized, driven by strong fundamental value hits and chaos-surviving alternates successfully balancing out formful early-week cards.

 

  1. Aggregate Observations: July 6 - July 12 Insights
  • Finger Lakes Dominance: The AI engine delivered spectacular, near-flawless execution at Finger Lakes, successfully identifying 7-of-8 winners on July 6 and sweeping the card with a perfect 8-for-8 performance on July
  1. The model accurately recognized fast dirt profiles and early presser biases while masterfully navigating basement class drops (TPN Prime dominance).
  • Scratch Failsafe Protocol Brilliance: The AI's Alternate Selection protocol proved its immense value again this week. Automatically bumping up alternates to fill gaps created by late scratches cleanly absorbed the volume and secured wins for horses like Carol Said No (July 8), Karey (July 9), and Movin' On Up (July 11), maximizing value even when morning-line favorites vanished.
  • Pace Mapping & Track Geometry: The AI's flow analysis was incredibly spot-on. "Lone Speed" and "Bias Survivor" models successfully identified extreme inside biases (e.g., Cold Spell and Soaring High on July 9). The pace meltdown logic correctly shielded off-the-pace contenders and successfully identified vulnerable early speed that succumbed to duels throughout the week.
  • Saratoga Chaos & Volatility: The model encountered high-variance chaos fields at Saratoga later in the week, particularly with 2-year-old maiden sprints and unexposed turf shippers. While race shape projections (like clustered front flights hitting a stamina wall) were often highly accurate, the AI occasionally fell victim to selecting the wrong beneficiary when deep closers failed to fire and mid-pack stalkers took the prize instead.
  • Model Adjustments & Blind Spots: To better capture late-week volatility, adjustments are recommended. Expanding the variance tolerance for mid-priced turf stalkers, relaxing True Speed (TS) ceiling restrictions for lightly raced improvers holding TPN Prime #1 shields, and heavily weighting outside "Clear Air" draws in juvenile sprints will help elevate fringe contenders into top-tier spots during extreme chaos scenarios.

THE MACHINE (AKA) TrackSmart AI isn’t a tip sheet or a picks website — it’s a professional-grade handicapping engine that works directly with the Past Performances (PPs) you already use from DRF, Brisnet, and Australia's Racing and Sports. Each version of TrackSmart AI — DRF, Brisnet, Harness, and International — is custom-engineered to read and interpret every printed detail in those PPs. No guessing. No databases. No shortcuts. The AI performs the deep work for you — comparing figures, detecting trainer intent, modeling pace, and uncovering hidden value plays — with the speed and accuracy of a professional analytics team. You stay in control of your handicapping while AI handles the heavy lifting. Pace projections, class and form analysis, TPN rankings, and betting strategy — all built from the same data you’d normally spend hours studying.