NBA Systems

Latest results

WEVShohei Ohtani Over 1.5 Total Bases+1.45u|LEVEnrique Hernández Over 0.5 Hits-1.00u|WEVShohei Ohtani Over 0.5 Hits+0.63u|LEVEnrique Hernández Over 0.5 Total Bases-1.00u|WEVGriffin Jax Over 11.5 Outs Recorded+0.94u|LEVGriffin Jax Under 11.5 Outs Recorded-1.00u|WEVGriffin Jax Under 3.5 Strikeouts+1.17u|LEVGavin Williams Under 6.5 Strikeouts-1.00u|WEVLiam Hicks Under 0.5 Hits+1.30u|LEVGavin Williams Over 15.5 Outs Recorded-1.00u|WEVCooper Pratt Under 0.5 Total Bases+1.16u|LEVBrayan Rocchio Under 0.5 Hits-1.00u|WEVShohei Ohtani Over 1.5 Total Bases+1.45u|LEVEnrique Hernández Over 0.5 Hits-1.00u|WEVShohei Ohtani Over 0.5 Hits+0.63u|LEVEnrique Hernández Over 0.5 Total Bases-1.00u|WEVGriffin Jax Over 11.5 Outs Recorded+0.94u|LEVGriffin Jax Under 11.5 Outs Recorded-1.00u|WEVGriffin Jax Under 3.5 Strikeouts+1.17u|LEVGavin Williams Under 6.5 Strikeouts-1.00u|WEVLiam Hicks Under 0.5 Hits+1.30u|LEVGavin Williams Over 15.5 Outs Recorded-1.00u|WEVCooper Pratt Under 0.5 Total Bases+1.16u|LEVBrayan Rocchio Under 0.5 Hits-1.00u|

All results

SYSTEM	MARKET	TYPE	DISTRIBUTION	STATUS	TODAY (ROWS / PRICED)	LIVE MAE (ENGINE / L5)	RESEARCH MAE (MODEL / BASE)	BRIER	BLEND c (t)
Points	Player Points	Prop

KEY FEATURES (RESEARCH MODEL)

Rolling L5 / L10 averages and EWM (half-life 8) of each stat and of minutes
Opponent-allowed rates
Rest days and back-to-back flags
Missing-teammate minutes and usage redistribution (experimental, off by default)

Against prices. No edge claimable. Accuracy gains over a rolling mean are 0.5 - 2.7% of MAE, the kind of gap a book's own projection already contains. Minutes and availability are the main driver the model does not have.

What the daily board runs. The daily board runs an empirical estimator: exponentially weighted game-log average, blended with a usage-adjusted rate, scaled by an opponent-allowed factor, with a negative-binomial or normal spread fitted from the league's own game-to-game variance. NFL means are calibrated on 2021-2025 outcomes (accuracy only: the pool of quoted players is over-projected by 3-7%). It does not model injuries, lineups, minutes, weather or teammate absences, and it has not been validated against prices.

Source: NBA props evaluation, 2026-10-14 (CRPS: 2025-26 season; Brier / ECE: proxy lines, PIT-recalibrated). Baselines are the best trailing-average forecaster in each study.