TrackSmart AI Weekly Scorecard: NYRA & Regional Tracks

Cumulative performance through October 4, 2026, with the September 28 – October 4 week in focus

TrackSmart AI | Prepared for Saratogabets | Week Ending October 4, 2026

1. Overview & Methodology

This scorecard covers the cumulative reporting period of December 26, 2025 through October 4, 2026, with a close look at the week of September 28 through October 4. The tracking dataset spans 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), Del Mar (DMR), Hollywood Casino at Charles Town Races (CT), Kentucky Downs (KD) and Keeneland (KEE).

The headline measure is the Top 4 Strike Rate: the share of races in which the AI’s four selections include the winner. A race counts as a hit if the winner sits anywhere in the Top 4, and the Avg Payout column tracks what those winning horses paid. This week added 115 races across Finger Lakes, Belmont Park, Saratoga Harness and Keeneland, bringing the cumulative sample to 2,261 races.

2. This Week at a Glance

Volume Expansion

The dataset grew to 2,261 total races with the addition of 115 races from September 28 through October 4. Finger Lakes, Belmont Park, Saratoga Harness and Keeneland all contributed.

Strike Rate Resilience

The cumulative Top 4 Strike Rate eased slightly, from 78.0% to 77.3% (1,747 of 2,261). The week itself brought high-variance conditions and weather anomalies. Even so, the AI found the winner in its Top 4 in 74 of 115 races (64.3%), with especially strong multi-day hit rates at Keeneland and Finger Lakes.

Value Normalization

The average payout on AI hits rose to roughly $8.07, up from roughly $7.98. Deep value identification and scratch-protocol mapping produced a run of large overlays: Flyhawk El Derecho ($38.16), Sunday’s Brunch ($35.72), Let Em Know ($27.38), Diliello ($27.14), La Puma ($25.84), Dotsy ($25.02) and White Sport Coat ($22.30).

System Integrity & Scratch Protocol

The automated scratch-adjustment protocol was important again this week. It moves “Next-Man-Up” alternates into active slots, which protected win rates and lifted winners such as Funny Factor ($22.08), Damavand ($7.48) and Right in Time ($15.38) into actionable ticket structures.

3. Daily Performance Breakdown

Prior totals reflect cumulative data through September 27. Daily breakdowns from earlier reports are condensed into the Prev. Totals row. Late scratches shifted runners up in the rankings across all cards this week, producing a number of top-tier hits and lifting the average payout.

4. Winner Distribution by Rank (Cumulative)

Taken together, the Top Pick and 2nd Selection account for 1,116 of the 1,747 hits, while the 3rd and 4th slots contribute 631 more. Those back-of-the-ticket slots are also where this week’s biggest prices came from, so the full Top 4 is doing real work and not just padding the ticket.

5. Cumulative Statistics Summary

6. This Week’s Structural Findings

The Scratch Protocol Keeps Paying

Sliding alternates up into the Top 4 after late scratches proved lucrative once again. The rule is simple and structural, and it caught real payout winners. Damavand ($7.48) moved from 5th to 3rd at Keeneland, and Funny Factor ($22.08) and Vekomancer ($3.62) were adjusted up into the Top 4 at Belmont Park.

Turf Routing & Deep Value

The turf algorithms were a highlight. On October 3 at Belmont Park the AI correctly swept every turf event on the card. Across the week it found strong value in stakes and turf routes, identifying late-kick beneficiaries and capturing overlays like Let Em Know ($27.38) and Dotsy ($25.02).

Pace Mapping on the Half-Mile Oval

The model identified vulnerable, contested early fractions well. At Saratoga Harness it located late-kick advantages on a half-mile oval and pulled Sunday’s Brunch ($35.72) and Flyhawk El Derecho ($38.16) out of unsettled pace flows.

Off-Turf Chaos & the Speed Gate Blind Spot

Weather and surface changes hurt the AI’s effectiveness on September 30 at Belmont Park, where the day finished at 12.5%. Races moved to the All-Weather Tapeta broke the model’s predictive footing. Rigid filters such as the “Speed Gate” restriction wrongly faded horses taking large class drops. That exposes a blind spot, and it needs an explicit override condition for stakes and allowance droppers.

7. AI’s Final Analysis: Building the Path Forward

1. Keep the scratch protocol exactly as it is. It has now protected win rates and surfaced overlays across multiple weeks. Any changes should be additive, not a rewrite.
2. Add a class-dropper override to the Speed Gate. When a race moves off the turf, a stakes or allowance dropper should not be faded by the Speed Gate alone. This is the most clearly identified fix from the week.
3. Flag surface changes as a risk condition. The September 30 Tapeta switch was the week’s one real failure. Races moved to a different surface deserve a visible caution and a review of which filters still apply.
4. Trust the turf and route work. The October 3 turf sweep at Belmont Park suggests the late-kick logic is calibrated well for stakes and turf routes. Confidence there can stay high.
5. Keep reading pace shape on small ovals. The Saratoga Harness results show the contested-fraction analysis finding late-kick winners on a half-mile track. Preserve that logic as the harness card continues.
6. Respect the full Top 4 when building tickets. Third and fourth selections produced some of the week’s biggest prices, so structures that drop them give up the value this model is finding.

8. Data Notes & Caveats

• Reporting period runs December 26, 2025 through October 4, 2026; this week’s window is September 28 through October 4.
• Prior totals (2,146 races, 78.0%, ~$7.98) reflect data through September 27 and are condensed into a single Prev. Totals row.
• This week’s additions came from Finger Lakes, Belmont Park, Saratoga Harness and Keeneland only; the other tracks in the dataset had no new races.
• The 74 of 115 weekly figure (64.3%) is the Top 4 hit rate for the week, consistent with the 1st–4th pick columns in the daily table.
• Rank-distribution percentages are shares of all 1,747 cumulative hits, not of all races.
• Average payouts are for AI hits only and are shown as reported; the cumulative figures are approximate (~).
• Single-day results, such as the 12.5% at Belmont Park on September 30, come from small samples and should be read alongside the cumulative totals.

TrackSmart AI: Cumulative Performance Report - NYRA Tracks

Reporting Period: December 26, 2025 – March 29, 2026

Track: Aqueduct (AQU)

2. Executive Summary: March 29 Update
   • Volume Expansion: The tracking dataset has grown to 392 total races with the addition of 25 races run across the March 27, March 28, and March 29 cards.
   • Strike Rate Resilience: The cumulative Top 4 Strike Rate settled at 77.6%. After struggling with speed-biased tracks and unexpected pace flows on Friday (50.0%) and Saturday (55.6%), the model rebounded beautifully on Sunday with a 75.0% strike rate.
   • Value Normalization: The Average Payout for AI hits adjusted slightly downward from ~$7.79 to ~$7.73. The weekend saw a mix of chalkier 1st-pick hits alongside excellent mid-tier value finds like Sheriff Bianco ($16.12) and Radio Red ($11.32).
   • Down-Ballot / Alternate Strength: Because the AI cannot alter its rankings once scratches are announced, bettors rely heavily on the model's static alternates (5th/6th rankings) to slide into the active Top 4. This structural depth proved highly valuable this weekend, catching several winners who were elevated by end-users following late
3. Daily Performance Breakdown

3. Winner Distribution by Rank (Cumulative)

4. Cumulative Statistics Summary

5. Aggregate Observations: Mar 27 - Mar 29 Insights
   • Static Pace Vulnerability (The Scratch Factor): The AI evaluates and projects pace based on the field exactly as it is On Mar 27 (Race 5), the model completely missed a $21.46 winner (Solomini's World) because the primary "Need-the-Lead" horse scratched. The AI could not dynamically recalculate the sudden lack of pace pressure, failing to foresee the winner inheriting an uncontested lead. Corrective Action: Develop an automated secondary "If Primary Speed Scratches" pace scenario flag for end-users. This will allow bettors to manually pivot their strategy when a race's fundamental flow is compromised by a scratch.
   • Stalker Penalties Meltdown Projections: The AI heavily downgraded tactical mid-pack horses in anticipated hot paces, missing winners like Hedge Ratio ($7.20) and Master of Arms ($13.52) because it rigidly favored perfect "lone speed" or "deep closer" profiles. Corrective Action: Increase the raw situational weighting for outside pressers/stalkers. Horses that can dictate their own engagement distance should not be as severely penalized in meltdown scenarios as rail-bound stalkers.
   • Age-to-Upside Multipliers: On Sunday, the AI missed Tapit Back ($7.30), leaning heavily on established older class-droppers and undervaluing a lightly raced 3-year-old filly facing heavily exposed older Corrective Action: Integrate a stronger age-to-upside developmental multiplier for lightly raced 3-year-olds facing strictly older, exposed maiden claimers.

TrackSmart AI Weekly Scorecard: NYRA & Regional Tracks

Cumulative performance through October 11, 2026, with the October 5 – October 11 week in focus

TrackSmart AI | Prepared for Saratogabets | Week Ending October 11, 2026

1. Overview & Methodology

This scorecard covers the cumulative reporting period of December 26, 2025 through October 11, 2026, with a close look at the week of October 5 through October 11. The tracking dataset spans 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), Del Mar (DMR), Hollywood Casino at Charles Town Races (CT), Kentucky Downs (KD) and Keeneland (KEE).

The headline measure is the Top 4 Strike Rate: the share of races in which the AI’s four selections include the winner. A race counts as a hit if the winner sits anywhere in the Top 4, and the Avg Payout column tracks what those winning horses paid. This week added 118 races across Finger Lakes, Belmont Park and Keeneland, bringing the cumulative sample to 2,379 races.

2. This Week at a Glance

Volume Expansion

The dataset grew to 2,379 total races with the addition of 118 races from October 5 through October 11. Finger Lakes, Belmont Park and Keeneland all contributed.

Strike Rate Resilience

The cumulative Top 4 Strike Rate eased slightly, from 77.3% to 77.0% (1,833 of 2,379). The week brought high-variance conditions and weather anomalies, with sloppy and yielding surfaces in play. Even so, the AI found the winner in its Top 4 in 86 of 118 races (72.9%). The week was highlighted by a perfect 9-for-9 sweep at Belmont Park on October 11 and an 8-for-8 sweep at Keeneland on October 7.

Value Normalization

The average payout on AI hits rose to roughly $8.15, up from roughly $8.07. Deep value identification, off-track adaptation and scratch-protocol mapping produced a run of large overlays: Free Advice ($49.58), Love Knicks Hart ($33.30), Our Preferred Pal ($25.64), Zomoroda ($23.24), Billy Bucchero ($19.92) and Insightful Miss ($19.66).

System Integrity & Scratch Protocol

The automated scratch-adjustment protocol was the story of the week. Mechanically moving “Next-Man-Up” alternates into active slots protected win rates and salvaged multiple cards, lifting unheralded mid-priced and longshot runners into actionable ticket structures when heavy favorites were scratched.

3. Daily Performance Breakdown

Prior totals reflect cumulative data through October 4; earlier daily breakdowns are condensed into the Prev. Totals row. Late scratches shifted runners up in the rankings across cards this week, securing a number of top-tier hits and lifting the average payout.

4. Winner Distribution by Rank (Cumulative)

The Top Pick and 2nd Selection account for 1,158 of the 1,833 hits, while the 3rd and 4th slots contribute 675 more. The back-of-the-ticket slots are again where the week’s biggest prices came from, so the full Top 4 is doing real work and not just padding the ticket.

5. Cumulative Statistics Summary

6. This Week’s Structural Findings

Scratch Protocol Validation & Field Dynamics

The mechanical rule of sliding alternates into the Top 4 after late scratches was the story of the week. This simple structural adjustment salvaged multiple race cards, moving lower-ranked horses up to catch payouts like Billy Bucchero ($19.92) at Belmont and Free Advice ($49.58) at Keeneland. The protocol coincided with a flawless 8-for-8 day on October 7 and a 9-for-9 sweep on October 11.

Maiden Chaos & Value Hunting

Maiden Special Weight and Maiden Claiming races full of lightly raced and debuting horses presented a lot of variance. The AI still trapped mid-priced value by identifying class drops and leaning on strong trainer and jockey combinations, snagging Insightful Miss ($19.66) as a 2nd choice over shorter-priced favorites.

Pace Mapping & Track Bias Realization

The projected Pace Scenario and Race Flow logic tracked reality closely. At Finger Lakes and Belmont, front-end speed and tactical “Garden Spot” stalkers dominated, validating the AI’s frequent weighting toward horses with high TS Ignition and TS Surge grades. That isolated wire-to-wire locks and supported strong multi-race tickets.

Off-Track Meltdowns & Perfect Sweeps

Sloppy dirt and yielding turf made for a volatile end to the week, especially on October 11. Despite heavy favorites scratching and large race-shape changes, the model adapted to pace meltdowns and delivered a 9-for-9 sweep at Belmont, placing 7 of the 9 winners in the 3rd-ranked position and keeping high-ceiling longshots on the ticket.

7. AI’s Final Analysis: Building the Path Forward

• Leave the scratch protocol alone. It has now protected win rates and surfaced overlays across several weeks running. Any change should be additive, not a rewrite.
• Keep the full Top 4 on the ticket. Seven of nine Belmont winners on October 11 came from the 3rd slot, and the 4th slot delivered Free Advice at $49.58. Structures that drop the back of the ticket give up exactly the value this model is finding.
• Treat off-track days as a feature to plan for. Sloppy and yielding conditions did not break the model this week; it adapted to pace meltdowns. Surface-change adjustments are worth keeping prominent in the process.
• Keep leaning on pace shape at Finger Lakes and Belmont. Front-end speed and stalkers with high Ignition and Surge grades were rewarded. That logic can keep its current weighting.
• Stay alert in maiden fields. Class-drop and trainer/jockey cues found value, but these races carry the most variance, so ticket sizing should reflect that.
• Watch the thin days. Belmont on October 9 (44.4%) and Keeneland on October 8 (40.0%) were the week’s softest cards. They are small samples, but they are worth tracking if the pattern repeats.

8. Data Notes & Caveats

• Reporting period runs December 26, 2025 through October 11, 2026; this week’s window is October 5 through October 11.
• Prior totals (2,261 races, 77.3%, ~$8.07) reflect data through October 4 and are condensed into a single Prev. Totals row.
• This week’s additions came from Finger Lakes, Belmont Park and Keeneland only; the other tracks in the dataset had no new races.
• The 86 of 118 weekly figure (72.9%) is the Top 4 hit rate for the week, consistent with the 1st–4th pick columns in the daily table.
• Rank-distribution percentages are shares of all 1,833 cumulative hits, not of all races.
• Average payouts are for AI hits only and are shown as reported; the cumulative figures are approximate (~).
• Single-day results, such as the 44.4% at Belmont Park on October 9, come from small samples and should be read alongside the cumulative totals.

TrackSmart AI - Cumulative Performance Report - NYRA Tracks

Reporting Period: December 26, 2025 – April 4, 2026

Track: Aqueduct (AQU)

2. Executive Summary: April 4 Update

   • Volume Expansion: The tracking dataset has grown to 420 total races with the addition of 28 races run across the April 2, April 3, and April 4 cards.

   • Strike Rate Resilience: The cumulative Top 4 Strike Rate held perfectly steady at 77.6%. The AI opened the week with a dominant 87.5% strike rate on Thursday and maintained a highly consistent 75.0% through Friday and Saturday's cards.

   • Value Normalization: The Average Payout for AI hits adjusted upward from ~$7.73 to ~$7.81. This was driven by an influx of chaotic deep value hits over the weekend, highlighted by Lika Rolling Stone ($25.64) and Mo Attitude ($17.06).

   • Down-Ballot / Alternate Strength: The rule to slide alternate selections (5th/6th rankings) into the active Top 4 when multiple scratches occur was the MVP of the week. This structural depth proved incredibly lucrative, catching multiple massive winners that were elevated into playable matrix slots by end-users.

3. Daily Performance Breakdown

3. Winner Distribution by Rank (Cumulative)

4. Cumulative Statistics Summary

5. Aggregate Observations: Apr 2 - Apr 4 Insights

   • Adaptability to Scratches (The Move-Up Rule): The algorithmic rule to automatically move alternates into the Top 4 playable matrix in the event of scratches was highly validated this week. Rampant scratches elevated massive payouts like Lika Rolling Stone ($25.64), That's Funny ($6.26), and El Grande O into playable positions. Observation: The AI's static deep-ballot (5th-8th) rankings are highly robust and critical for protecting exotic structures on days with high scratch volume.

   • Chaos Diagnostics vs. Trip Executions: The AI's macro-level pace mapping remains elite—it successfully flagged "High Chaos" and "Pace Meltdowns" prior to several massive upsets (e.g., Race 4 and Race 8 on Apr 4). However, it occasionally misdiagnosed the specific beneficiary. In Race 8, the AI correctly predicted a destructive pace duel, but missed 15-1 Fiddling Felix because it didn't anticipate the jockey entirely abandoning the horse's usual early-speed run style to execute a deep-closing trip. Corrective Action: Implement dynamic run-style flexibility algorithms that account for alternative trip scenarios and jockey intent when a destructive pace duel is heavily projected.

   • Layoff Penalties vs. Class Proven Runners: On April 2, the AI correctly mapped a slow pace but entirely dismissed Hello Beauty ($10.08), heavily penalizing the horse for declining numbers off a layoff while ignoring back-class. Corrective Action: Reduce the layoff penalty weight for class-proven runners, or implement a high-percentage connection modifier (e.g., Flavien Prat) to prevent logical horses from dropping below the fringe threshold.

   • Bottom-Tier Maiden Volatility: The AI completely dismissed 7-1 Icy Legs on April 3 based on poor raw speed numbers. Corrective Action: Soften the raw speed figure gap penalties in basement-level Maiden Claiming dirt routes. Marginal trip improvements in these fields can yield massive form reversals that rigid historical data struggles to capture.