Del Mar RacesToday's Card
Methodology & Transparency

We looked for a betting edge. We didn't find one. Here's exactly what we built instead.

Most handicapping sites either oversell a model's power or hide the methodology entirely. We do neither. Every claim on this site is grounded in a published, locked pre-registration — and the honest answer from the data is: the Del Mar win pool is efficient. What we've built is the most complete information product for Del Mar racing, not a guaranteed money-maker.

Pre-registered · git commit 396084aDel Mar 2021–2025 · 5 seasons7,154-runner training set
📋
The bottom line from the research

Across 8 independent analyses on 2+ years of holdout data, no fundamentals-based model — linear or modern ML — achieves positive ROI against the Del Mar win pool after the ~17% takeout. The market is efficient at this track. The only potentially-live signal is forward live-tote microstructure(steam moves at decision time), which we're testing on the 2026 meet — paper trade only, no real money until we have powered evidence.

Win-Brier: 0 of 14 models OOSFinish-order PL: 0 of 8Exotics ROI: negative across the boardBenter combo: adds nothing OOS

How we built it

01
Collect the data

BRIS single-file past performances for every Del Mar card, 2021–2025. Five years of 229 race-day cards, 7,000+ runners in the training set.

02
Pre-register the methodology

Before touching the data, we locked the train/validate/test split and every modeling decision in a public git commit (commit 396084a, 2026-06-26). This prevents retrofitting.

03
Build the model

A calibrated logistic ranker on BRIS fundamentals: speed figures, pace, run-style, days-since-last, morning-line odds. Trained on 2021–22 only. Never re-fit on validation data.

04
Test for a betting edge

Eight independent methods across two years of holdout data: Brier score, ROI by odds band, exotics, Harville finish-order, Benter combination, a 20-agent sweep. Result: no model clears the ~17% takeout. The edge is closed.

05
Ship the honest product

The calibrated probability estimates are accurate and useful for understanding a race — they're just not profitable bets. We ship them as information, not tips.

What the model actually does well

CALIBRATION CURVE · 2021–22 TRAIN

The model's probability estimates are well-calibrated: when it says a horse has a 25% chance of winning, roughly 1-in-4 of those horses win. The curve hugs the diagonal. That's useful for understanding race dynamics — it just doesn't translate into profit because the tote already prices the same information.

perfect Predicted probability 0% 100% 0.25.50.75 Actual win rate
WHAT THE MODEL IS GOOD FOR
  • Ranking the field for show programs + preview content
  • Calibrated win probabilities for honest race display
  • Identifying pace scenarios + style clashes
  • Grounding AI-generated race narratives in real numbers
WHAT IT CANNOT DO
  • Generate positive ROI against the takeout
  • Predict first-time starters better than the market
  • Profitably exploit layoff returners or lightly-raced horses
  • Outperform a Benter blend on finish-order

Pre-registration + grading

WHY PRE-REGISTRATION MATTERS

It's easy to find a strategy that looks good in hindsight — the hard part is knowing whether it works going forward. We locked the train/test split and every modeling choice before analyzing the holdout data. The locked pre-registration lives in the git repo as an immutable commit (396084a) and can be independently audited. The forward 2026 conditioner flags are also pre-registered: if they produce a result, you can verify we didn't cherry-pick it.

Train: 2021–22 (7,154 runners)Validate: 2023 (3,395 runners)Lockbox: 2024–25 (one read, ever)Forward 2026: paper-trade first
HOW WE GRADE OURSELVES

Every public prediction is scored as a flat $2 win bet. The scoreboard onSystemsshows ROI, CLV (closing-line value), win rate, and drawdowns — including a mid-meet losing streak. Nothing is hidden. The honest expectation heading into the 2026 meet is approximately break-even; any edge would be a genuine discovery.

HOW WE GRADE EVERYONE ELSE

The pundit leaderboard onSystemsgrades every public handicapper we aggregate — starting with the track's own selections, and additional public outlets as each is ToS-cleared — all on the same flat-$2 metric. Our honest expectation is that nobody, us included, clears the takeout; the meet will show it either way. That's radical honesty: if any source consistently does, we'll say so.

A pricing pattern in small fields

HISTORICAL OBSERVATION · NOT A BET

In our 2025 held-out test season, favorites racing in fields of 8 or fewer lost money when backed at a flat $2 win bet: −27.5% ROI(n=221, 95% CI −42% to −12%). That wasn't because they won less often — their win rate (34.4%) was almost identical to favorites in bigger fields (34.3%). The difference is price: small-field favorites go off shorter than their actual win rate justifies.

We're not calling this an edge. n=221 is below the 300-runner bar we hold ourselves to for a reportable result, it hasn't been confirmed against live closing odds, and it says nothing about whether any individual favorite wins or loses — the market's win-probability pricing is not beaten by anything in our research. And it is nota fade: an overbet cohort does not imply a profitable bet against it. The takeout applies to the other side too, exchange commissions and this sub-300 sample erase any paper gap, and we make no claim that laying or betting around these favorites wins. It's a descriptive pricing observation about one cohort, published pre-registered the same way everything else here is.

n = 221 · 2025 test seasonROI −27.5% · CI [−42%, −12%]Not forward-verified

What we're still testing

LIVE 2026 FORWARD TESTpaper-trade only · confirmed edge required before real money

The one signal the historical data can't disprove is live-tote microstructure: steam moves in the closing minutes before post that the public is slow to follow. We've pre-registered six conditioned-steam flags and wired them into every captured runner starting opening day (~Jul 17). The test runs on an anytime-valid e-process: we can stop early if the signal is clearly null, or declare when it's powered. Paper trade first; the bar for real money is a statistically powered positive result.

All research is exploratory. Past performance is not indicative of future results. This site does not provide investment advice or guarantee returns. Wagering involves risk — please play responsibly. 1-800-GAMBLER.