CFB Betting Edge

2025 · Week 9 · Big Ten · backtest — what the model predicted vs what happened, and vs the market
Week 9 backtest · Big Ten · 7 games — what the model predicted vs what happened
Straight up
7–0100%
ATS vs close
4–2 · 1P67%
Model margin MAE
12.6
Market margin MAE
13.1
→ model's margins were closer than the market
Results — model read vs the final score + how the closing-line lean held up
Wisconsin @ OregonFinal 721
Model
pred Oregon 18.1 · actual Oregon 14
winner Oregon
ATS vs close
leaned Wisconsin +31.5Cover ✓
margin err: model 4.1 · mkt 17.5 · closer
UCLA @ IndianaFinal 656
Model
pred Indiana 18.0 · actual Indiana 50
winner Indiana
ATS vs close
leaned UCLA +27.5Miss ✗
margin err: model 32.0 · mkt 22.5 · mkt closer
Model
pred Nebraska 15.4 · actual Nebraska 7
winner Nebraska
ATS vs close
leaned Nebraska -7.0Push
margin err: model 8.4 · mkt 0.0 · mkt closer
Minnesota @ IowaFinal 341
Model
pred Iowa 10.3 · actual Iowa 38
winner Iowa
ATS vs close
leaned Iowa -7.5Cover ✓
margin err: model 27.7 · mkt 30.5 · closer
Model
pred Washington 3.3 · actual Washington 17
winner Washington
ATS vs close
leaned Illinois +3.5Miss ✗
margin err: model 13.7 · mkt 13.5 · mkt closer
Rutgers @ PurdueFinal 2724
Model
pred Rutgers 3.8 · actual Rutgers 3
winner Rutgers
ATS vs close
leaned Rutgers +2.5Cover ✓
margin err: model 0.8 · mkt 5.5 · closer
Model
pred Michigan 12.8 · actual Michigan 11
winner Michigan
ATS vs close
leaned Michigan State +13.5Cover ✓
margin err: model 1.8 · mkt 2.5 · 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.