John-Z's Overlay · Trifecta ATM

Sat, May 16

Race 1

Clm 32000

Post: 1:10 · 6f · Dirt · $60K purse · 7 runners

New — Ask Claude Opus about this race Why a horse rates the way it does, what the trifecta ticket means, where the public might be wrong.

Pace shape

7 runners

Hot pace

6 early types pressing for the lead — expect a fast pace, favors closers (P/S).

2 E — pure early 4 EP — early/presser 1 P — presser

Projected speed

Trifecta shape

Competitive

Model has no clear edge — every ticket structure is steeply negative-EV. Skip, or treat as an entertainment bet and size accordingly.

3-horse box on posts 4, 1, 2

The model's most-likely-to-cash structure (informational — not a bet recommendation).

Cost

$6.00

6 combos

Hit prob

6.9%

simulated

Typical payout if hit

$33.54

mean $35.18

Expected ROI

-59.8%

net $-3.59

  • · Most-likely-to-cash structure: 3-horse box on posts [4, 1, 2] — hits 6.9% of simulated runs
  • · At $6 stake, a typical cash pays ≈ $34 (mean $35; trifecta payoffs are heavy-tailed). Estimated from the public pool, validated against archive payoffs.
  • · Multiple legitimate contenders — model is less concentrated.

A Top picks

4, 1

B Contenders

2, 3, 5

C Value-edge longshots

7, 6

Other ticket structures (5)
Ticket Cost Hit prob Typical payout ROI
1×3×3 key (top pick) $6.00 5.4% $27.75 -75%
2×4×4 part wheel $12.00 10.9% $30.81 -70%
1×4×4 key (top pick) $12.00 9.3% $30.81 -76%
1×5×5 key (top pick) $20.00 14.0% $32.43 -72%
2×5×5 part wheel $24.00 18.8% $34.07 -70%

Hit prob is the model's per-race PL distribution. "Typical payout" is the median cash, weighted by the public pool's odds (not the model's own picks) and calibrated to actual historical trifecta payoffs — so it reflects what the tote really pays, not the model's disagreement. Walk-forward backtests show pari-mutuel takeout (~16-26%) is too steep to consistently clear at this data scale — these are tipsheet outputs, not bet recommendations.

Top-4 ITM concentration: 65% · Top 4 cover 1.95 of the 3.00 expected ITM finishers

Field

Click any horse name for the per-horse breakdown (last-10-races chart, SHAP feature contributions, full PP table).

PP Horse ML Pred Close Pred Fig Win ITM% Edge
4APBEARY FUNNY2.5-12.7-185.918%52%-21%
1AEFACTUALLY CORRECT4.0-15.3-186.918%52%·+1%
2BEPNABOKOV4.0-14.2-185.418%52%·+1%
3BEPBIG HAT WILLIE3.0-13.8-185.213%39%-24%
5BEPCLANCY FANCY4.5-15.9-183.212%37%-9%
6CESTEWIE10-112-181.811%36%+13%
7CEPGRAYWING15-116-180.710%31%+15%

Sort the table by clicking column headers. Edge = our predicted ITM% minus the public-implied ITM% (live odds when present, ML otherwise); green ▲ ≥ +5pp, red ▼ ≤ −5pp. See How to Use for the math.

Ask Claude Opus

Questions about the model's predictions for Race 1 · Sat, May 16 · Belmont at The Big A. Powered by Claude Opus 4.7.

Ask anything about the field, the trifecta ticket, or why the model rates a horse the way it does.

Limited to 30 questions per day per visitor. Answers are model-generated and may be incorrect — not betting advice.