CFB Betting Edge

2025 · Week 12 · Big Ten · backtest — what the model predicted vs what happened, and vs the market
Week 12 backtest · Big Ten · 8 games — what the model predicted vs what happened
Straight up
8–0100%
ATS vs close
4–450%
Model margin MAE
9.4
Market margin MAE
6.9
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
UCLA @ Ohio StateFinal 1048
Model
pred Ohio State 26.4 · actual Ohio State 38
winner Ohio State
ATS vs close
leaned UCLA +33.0Miss ✗
margin err: model 11.6 · mkt 5.0 · mkt closer
Minnesota @ OregonFinal 1342
Model
pred Oregon 19.0 · actual Oregon 29
winner Oregon
ATS vs close
leaned Minnesota +26.5Miss ✗
margin err: model 10.0 · mkt 2.5 · mkt closer
Model
pred Indiana 11.6 · actual Indiana 24
winner Indiana
ATS vs close
leaned Wisconsin +28.0Cover ✓
margin err: model 12.4 · mkt 4.0 · mkt closer
Model
pred Illinois 11.6 · actual Illinois 18
winner Illinois
ATS vs close
leaned Maryland +16.5Miss ✗
margin err: model 6.4 · mkt 1.5 · mkt closer
Purdue @ WashingtonFinal 1349
Model
pred Washington 8.9 · actual Washington 36
winner Washington
ATS vs close
leaned Purdue +14.5Miss ✗
margin err: model 27.1 · mkt 21.5 · mkt closer
Iowa @ USCFinal 2126
Model
pred USC 5.1 · actual USC 5
winner USC
ATS vs close
leaned Iowa +6.5Cover ✓
margin err: model 0.1 · mkt 1.5 · closer
Model
pred Michigan 8.4 · actual Michigan 2
winner Michigan
ATS vs close
leaned Northwestern +10.0Cover ✓
margin err: model 6.4 · mkt 8.0 · closer
Model
pred Penn State 16.6 · actual Penn State 18
winner Penn State
ATS vs close
leaned Penn State -7.0Cover ✓
margin err: model 1.4 · mkt 11.0 · closer
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.