TrackSmart AI: Cumulative Performance Report

Reporting Period: December 18, 2025 – January 25, 2026

Tracks: Gulfstream Park (GP), Aqueduct (AQU), Fair Grounds (FG), Tampa Bay Downs (TAM)

1.    Executive Summary: January 25 Update

• Volume Expansion: The dataset has expanded to 432 Total Races.
• Continued Stability: Following the volatility of the Pegasus World Cup on Saturday, Sunday's results brought a return to normalized strike Tampa Bay Downs delivered a consistent 77.8% accuracy, while Gulfstream Park rebounded to 72.7%, stabilizing the long-term trend lines.
• High-Value Captures: The model continued to find value at Gulfstream Park on Sunday, with average payouts for hits remaining While not reaching the "Mega Day" heights of Saturday's payouts, the model successfully identified value plays in the Top 4, including winners paying $15.40 and $12.20.
• Resilience: The cumulative Strike Rate remains robust at 3%, absorbing the volume of a busy weekend while maintaining an overall accuracy rate above the target threshold.

2.       Daily Performance Breakdown

The table below details the performance progression, listing the results from January 22 through January 25 separately by track.

*Prev. Totals includes all data from Dec 18 through Jan 21.

3.       Winner Distribution by Rank (Cumulative)

The distribution of winners across the AI's Top 4 selections shows a slight shift toward the "Secondary" (2nd) selection following Sunday's results at Tampa Bay.

4.       Cumulative Statistics Summary

5.       Daily Observations: Weekend Wrap-Up

January 24: The "Mega Day" Stress Test

• Tampa Bay Downs (Standard Profile):
• The Baseline: Tampa Bay represented a standard handicapping The model performed exactly as designed, hitting 77.8% of winners.
• The Logic: With standard field sizes and established form, the AI's logic held firm, identifying 5 of the 7 winners in its Top 2 selections.
• Gulfstream Park (The Pegasus "Chaos"):
• The Challenge: The Pegasus World Cup card featured maximum field sizes, European shippers, and extreme
• The Reality: The Strike Rate dropped to 2% due to "chaos" results, but the ROI skyrocketed.
• The Silver Lining: The "Alternate" (4th) and "Secondary" (2nd) selections saved the day by identifying massive longshots, including the Pegasus winner ($45.20) and a $50.60 upset in Race

January 25: Recovery and Consistency

• Tampa Bay Downs (The Steady Hand):
• Performance: The model delivered another solid 80% strike rate (7/9 winners).
• Missed Opportunities: The two misses (Races 7 and 8) were mid-range horses rather than chaos Specifically, the model under-weighted the closing capability of El Ma'any in Race 7 and over-penalized Final Drama in Race 8, suggesting minor adjustments are needed for pace weighting in mid-class turf routes
•  
• Gulfstream Park (Value Stabilization):
• Performance: Gulfstream bounced back with a 70% strike rate (8/11 winners).
• Value Found: The model successfully identified value plays, such as Friolento ($15.40) as a 2nd pick and Flying Liam ($12.20) as a 4th pick.
• Logical Misses: The misses were structural rather than In Race 8, the model's strict "Extreme Layoff" penalty filtered out the winner The Brigade. In Race 6, the model correctly identified Z First as a contender but penalized it for a projected "Disadvantaged Speed" scenario that the horse successfully overcame.

TrackSmart AI: Cumulative Performance Report

Reporting period through – February 1, 2026

Tracks: Gulfstream Park (GP), Aqueduct (AQU), Fair Grounds (FG), Tampa Bay Downs (TAM)

1.     Executive Summary: February 1 Update

• Volume Expansion: The dataset has crossed the 500-race milestone, reaching 509 total races with the addition of Sunday cards at Gulfstream Park and Tampa Bay
• Performance Resilience: The cumulative Strike Rate remains robust at 8%, slightly adjusted from 77.0% as a near-perfect performance at Tampa Bay (8 of 9 winners) balanced a challenging, chaos-filled afternoon at Gulfstream Park (5 of 9 winners).
• Metric Adjustment: The Average Payout settled at ~$8.35. While Gulfstream produced some higher-priced upsets that the model missed, the winners identified at Tampa Bay were primarily logical favorites, keeping the average

2.        Daily Performance Breakdown

The following table reflects the current weekly cycle starting January 28, 2026. All data prior to this date is consolidated in "Previous Totals."

3.        Winner Distribution by Rank (Cumulative)

4.        Cumulative Statistics Summary

5.        Daily Observations: February 1 Insights

Tampa Bay Downs (Favorites & Logic)

• Near-Perfect Calibration: The AI was exceptionally sharp at Tampa Bay, correctly identifying 8 of 9 The "Top Pick" was particularly potent, winning 5 times (Races 1, 3, 4, 5, 6).
• Alternate Value: The "Alternate Selection" (Scratch Protection/4th Pick) proved essential in Races 2 and 8, catching winners that were slightly lower on the Power probability curve but fundamentally sound.
• One Outlier: The only miss was Race 9, where a massive longshot ($49.60) returning from a long layoff defeated the logic-based selections.

Gulfstream Park (Pace & Trip Dynamics)

• Strong Start, Chaotic Finish: The model performed well early, identifying logical winners in Races 1, 2, 3, 4, and However, the later races saw significant deviation from projected scripts.
• Pace Projection Adjustments: The model struggled with "pace meltdown" projections in the later In Race 5 and Race 8, the AI anticipated a collapse that would favor closers, but tactical speed/stalkers held up better than expected.
• Chaos Result: Race 6 featured a massive upset ($69.60) by a 33-1 longshot making a wide move that was not visible in the fundamental figures or back-class ratings.

TrackSmart AI: Cumulative Performance Report

Reporting Period: December 18, 2025 – February 7, 2026

Tracks: Gulfstream Park (GP), Aqueduct (AQU), Fair Grounds (FG), Tampa Bay Downs (TAM)

1.    Executive Summary: February 7 Update

• Volume Expansion: The dataset has expanded to 559 total races with the addition of the Saturday card at Tampa Bay Downs (11 races).
• Performance Resilience: The cumulative Strike Rate rebounded to 4% (up from 76.1%). The model delivered an exceptional daily strike rate of 90.9% (10-for-11) at Tampa Bay, significantly outperforming the historical baseline.
• Metric Adjustment: The Average Payout held steady at ~$8.41 (virtually unchanged). Tampa Bay provided solid value ($8.28 avg on hits), including two double-digit payouts ($11.60 and $18.20), balancing the lower-priced
• Selection Shift: The "Top Pick" remained quiet with only 2 wins. However, the model’s secondary depth was the star of the day; the 2nd Selection captured 4 wins, including key strikes in the Stakes races, effectively driving the day's high accuracy.

2.       Daily Performance Breakdown

The following table reflects the current cycle. All data prior to the Feb 5 update remains consolidated in "Prev. Totals."

3.       Winner Distribution by Rank (Cumulative)

4.       Cumulative Statistics Summary

5.       Daily Observations: February 7 Insights

Tampa Bay Downs (Stakes Dominance & Value)

• Stakes Dominance: The AI performed exceptionally well in the feature races, identifying the winner within the Top 2 selections for all four stakes (Minaret, Suncoast, Pelican, and Sam F. Davis).
• Vulnerable Favorite Survival: In Race 1, the AI flagged the eventual winner (#9) as a "Vulnerable Favorite" due to surface concerns but kept him ranked 4th due to This defensive ranking successfully saved the strike rate despite the negative trip projection.
• Value Captures: The model successfully identified significant value overlays that the public underestimated, including Neshume ($18.20) in Race 8 (ranked 3rd) and Concrete Glory ($14.40) in Race 10 (ranked 2nd).
• Missed Winner Analysis (Race 9):
• The Miss: The AI missed Kokomotion ($23.80), a First Time Starter (FTS).
• The Cause: The model penalized the FTS status heavily because the trainer's stats were weaker compared to elite barns (like Chad Brown) in the same The horse was marked as a "Non-Contender" despite a "sharp workout" note.
• Adjustment: In future maiden turf routes, the "sharp workout" variable will be weighted more heavily against trainer percentages to better identify live longshot debut runners.

TrackSmart AI: Aqueduct 5-Day Performance Report

Reporting Period: February 11 – February 15, 2026

Track: Aqueduct Racetrack (AQU)

Algorithm Parameters: Pure Data-Driven (Blind to Morning Line, Odds, and Public Support)

1.     Executive Summary

Over the five-day racing week at Aqueduct, the AI successfully handicapped 44 races relying exclusively on fundamental speed, pace, and class data. By operating completely blind to the morning lines and public betting pools, the model bypassed crowd bias and successfully isolated value overlays based purely on biological and trip metrics.

The algorithm secured an exceptional 79.5% Top 4 Strike Rate across the week, catching 35 winners. Even without recognizing odds, the model naturally guided selections toward robust payouts, culminating in a strong $10.90 average payout on Sunday and a blended weekly average of ~$7.57 per hit.

2.        Daily Performance Breakdown

3.        Winner Distribution by AI Rank

The distribution of winners reinforces the model's accuracy at the top of the ticket. The primary and secondary selections accounted for over 65% of all successful hits this week.

4.        Track Dynamics & Algorithmic Insights

• Track Bias Navigation: The track surface played fast all week, with a distinct rail/inside speed advantage noted earlier in the week that gradually shifted to a fairer profile by the Because the AI relies solely on data, it successfully adjusted to these micro-changes in the track profile without being swayed by the public over-betting inside horses once the bias dissipated.
• Pace Meltdowns Genuine Speed: The model excelled at differentiating between vulnerable early speed and resilient front-runners. On Sunday, it correctly anticipated a pace collapse, pulling deep closers like Tahila ($19.72) and Bourbon N Lace ($17.78) into the top selections based purely on pace-shape metrics, completely ignoring their high odds.
• Area for Refinement: The primary blind spot this week occurred in routes where the AI misidentified the controlling speed due to inside gate pressure (e.g., assigning a "loose on the lead" projection to the wrong horse). Applying heavier weighting to tactical, off-the-pace ability in these specific route scenarios will tighten up the few missed