CFB Betting Edge

2025 · Week 13 · Big Ten · backtest — what the model predicted vs what happened, and vs the market
Week 13 backtest · Big Ten · 8 games — what the model predicted vs what happened
Straight up
7–188%
ATS vs close
2–529%
Model margin MAE
14.1
Market margin MAE
13.0
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Model
pred Ohio State 21.2 · actual Ohio State 33
winner Ohio State
ATS vs close
leaned Rutgers +28.5Miss ✗
margin err: model 11.8 · mkt 4.5 · mkt closer
Model
pred Iowa 16.6 · actual Iowa 3
winner Iowa
ATS vs close
leaned Michigan State +17.5Cover ✓
margin err: model 13.6 · mkt 14.5 · closer
USC @ OregonFinal 2742
Model
pred Oregon 6.6 · actual Oregon 15
winner Oregon
ATS vs close
leaned USC +11.0Miss ✗
margin err: model 8.4 · mkt 4.0 · mkt closer
Model
pred Northwestern 5.0 · actual Northwestern 3
winner Northwestern
ATS vs close
leaned Northwestern -4.0Miss ✗
margin err: model 2.0 · mkt 1.0 · mkt closer
Model
pred Penn State 4.8 · actual Penn State 27
winner Penn State
ATS vs close
leaned Nebraska +7.0Miss ✗
margin err: model 22.2 · mkt 20.0 · mkt closer
Model
pred Illinois 2.5 · actual Wisconsin 17
winner Illinois
ATS vs close
leaned Wisconsin +8.5Cover ✓
margin err: model 19.5 · mkt 25.5 · closer
Washington @ UCLAFinal 4814
Model
pred Washington 9.5 · actual Washington 34
winner Washington
ATS vs close
leaned UCLA +10.5Miss ✗
margin err: model 24.5 · mkt 23.5 · mkt closer
Michigan @ MarylandFinal 4520
Model
pred Michigan 14.0 · actual Michigan 25
winner Michigan
ATS vs close
model matched the close — no lean
margin err: model 11.0 · mkt 11.0 · tie
The model beats SP+ but not the closing line (ATS ≈ break-even). “Model−Mkt” is the gap between our projected home margin and the market's implied margin — a read on disagreement, not a profitable edge. Upcoming games have no closing line yet, so the market number marked ~ is the consensus midpoint of the best posted spreads across books.