Moneyline

Research only by policy. In the backtest it is not measurably more accurate than the league-wide rate.

Research only: Tier 3 by policy. Published for context, never as a basis for a bet, until a deliberate product change promotes it. Tier 3: Research only until proven.

The backtest

engine v14 · every graded game · walk-forward

Graded962over 72 dates

Skill vs league rate1.3%-0.4% to 2.9% (95%)

Predicted, on average51.2%what happened: 50.6%

Calibration slope0.811.00 is ideal; 0.80–1.20 passes

Ranking (AUC).563.500 is a coin flip

Skill is how much lower the Brier score of the served number is than always guessing the league-wide rate known at the time. Every date is predicted using only earlier dates, with calibration curves refit each date the way the site serves them.

The live test · engine v14

0 of 200 settled results · 0 of 7 dates

Only predictions frozen before first pitch, under the engine now serving, count. The count restarts with every engine version, which is why nothing is Validated yet.

Against the book's closing price

Book more accurate

Log loss, model minus the no-vig closing price: +0.023 (95% interval +0.003 to +0.043) on 81 predictions over 9 dates, engine v8. Positive means the book was more accurate. This comparison changes no status; it answers whether the number is a reason to bet.