ST Model Accuracy

Out-of-sample backtests of the ST Model — projections vs. what actually happened, and the game model vs. real outcomes
Batter projections
Beat the Marcel baseline by 3% on full-season accuracy · p10–p90 coverage 80% (2025 backtest, 2,772 preds)
Game model vs results
Brier 0.2448 vs home-field base 0.2489 · picks the winner 56% (17,881 games)
Player Accuracy
per 650 PA vs Marcel · 2,772 predsskill 3%p10–p90 cov 80%
StatNModelBaseSkillCov
Power
Home Runs3086.196.17-1%85%
Doubles3085.245.22-0%82%
Triples3081.541.64+6%83%
Run Production
Runs30810.1510.6+4%82%
RBI30813.0813.1+0%74%
Contact & Speed
Hits30811.7212.22+4%83%
Stolen Bases3085.15.52+8%82%
Plate Discipline
Walks30810.0410.19+2%77%
Strikeouts30819.1419.43+2%76%
Game Model — Out-of-Sample Backtest
backtest
SeasonGamesBrierBaseWin%Margin MAETotal MAEVegas MAEBeat%
20252,4250.24450.248256%3.553.7
20242,4270.24550.249555%3.473.6
20232,4290.24560.249656%3.483.7
20222,4240.24300.248957%3.363.9
20212,4260.24550.248656%3.473.8
20208950.24490.247556%3.613.8
20192,4270.24430.249156%3.563.9
20182,4280.24490.249255%3.454.0
Overall17,8810.24480.248956%3.483.8
The model's pre-game win probability is scored by Brier against every completed game's outcome; a Brier below the home-field Basemeans it adds signal beyond "home teams win." Margin/Total MAE measure the projected score. Vegas MAE / Beat% read — for this sport: the free odds feed carries no historical closing lines yet, so those columns populate as line history accrues.