John-Z's Overlay · Trifecta ATM

Sun, May 3

Race 1

Md 12500

Post: 12:50 · 5.5f · Dirt · $29K purse · 8 runners · LIVE Trifecta math uses live odds for 8 of 8 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

8 runners

Hot pace

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

4 E — pure early 1 EP — early/presser 1 P — presser 1 S — closer 1 Unclassified

Projected speed

1 of 8 runners have no BRIS run-style code (often first-time starters); narrative may understate the true pace.

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.

1×4×4 key (top pick) on posts 5, 8, 7, 1, 2

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

Cost

$12.00

12 combos

Hit prob

17.2%

simulated

Typical payout if hit

$44.25

mean $66.06

Expected ROI

-5.6%

net $-0.67

  • · Most-likely-to-cash structure: 1×4×4 key (top pick) on posts [5, 8, 7, 1, 2] — hits 17.2% of simulated runs
  • · At $12 stake, a typical cash pays ≈ $44 (mean $66; trifecta payoffs are heavy-tailed). Estimated from the public pool, validated against archive payoffs.
  • · Multiple legitimate contenders — model is less concentrated.

A Top picks

5

B Contenders

8, 7, 1

C Value-edge longshots

2

Other ticket structures (5)
Ticket Cost Hit prob Typical payout ROI
A key, B in 2nd, A+B+C in 3rd $9.00 14.6% $38.12 -10%
1×3×3 key (top pick) $6.00 11.5% $38.12 -18%
3-horse box $6.00 13.9% $32.73 -22%
1×5×5 key (top pick) $20.00 21.0% $60.76 -14%
2×4×4 part wheel $12.00 21.0% $36.79 -29%

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: 75% · Top 4 cover 2.25 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 Live Pred Fig Win ITM% Edge
5AEHOPE TOWN GIRL3.0-12.4-1·3.0-172.926%67%·+4%
8BETIE IT WITH A BOW2.0-11.7-12.5-168.621%60%-13%
7BEPDO I LOOK WORRIED4.0-14.4-1·4.0-166.819%56%·+5%
1BEFANTASY WORLD3.5-13.7-15.0-163.313%43%·+0%
2CSILITHYIA10-114-114-158.89%31%+14%
4PVANESSA'S WISH12-123-1·10-159.75%20%·-4%
6EFLOWERBOMB15-127-110-157.15%18%-5%
3LOVE OF J20-144-17.0-141.32%6%-26%

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. Live column: ↓ green = ≥25% shorter than ML (money horse); ↑ red = ≥25% longer (drifting). See How to Use for the math.

Ask Claude Opus

Questions about the model's predictions for Race 1 · Sun, May 3 · Gulfstream Park. 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.