CFT Model Accuracy

Out-of-sample backtests of the CFT Model's calibrated engine — projections vs. what actually happened, and vs. market closing lines
Player projections
Beat the naive baseline by 11% on per-game accuracy · p10–p90 coverage 44% (2025 backtest, 7,762 preds)
Team margins vs market
Model MAE 13.35 vs market 12.2 · beats the line 49.6% (5,297 games)
Player Accuracy
per-game rate vs naive · 7,762 predsskill 11%p10–p90 cov 44%
StatNModel /gBase /gSkillCov
Passing
Pass Yards29465.4385.56+24%0%
Pass TDs2940.660.7+6%0%
Pass INTs2940.260.38+31%0%
Completions2945.257.06+26%0%
Rushing
Rush Yards93719.7521.5+8%21%
Rush TDs9370.280.27-5%16%
Receiving
Receptions17850.881.02+13%62%
Rec Yards178511.5712.94+11%64%
Rec TDs11420.170.19+12%72%
Team Margins vs Market Closing Lines
backtest
SeasonGamesModel MAEMarket MAEBeat%Corr·MCorr·Mkt
202580913.0811.8251.5%0.570.67
202480313.1312.0648.7%0.560.64
202379712.9812.1150.8%0.590.66
202278413.2812.0548.1%0.570.64
202178114.0112.5846.6%0.560.66
202053813.7912.8753%0.580.64
201978513.3712.1749.3%0.630.71
Overall529713.3512.249.6%0.580.66
Lower MAE = closer to the real margin. Matching the market's MAE means we're at market level; a Beat% above 50 implies positive expectation against the closing line. The model never sees the line — it's stored only to benchmark honestly.