CFB Betting Edge

2024 · 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
6–275%
ATS vs close
5–363%
Model margin MAE
12.0
Market margin MAE
12.9
→ model's margins were closer than the market
Results — model read vs the final score + how the closing-line lean held up
Model
pred Michigan 16.6 · actual Michigan 44
winner Michigan
ATS vs close
leaned Michigan -10.5Cover ✓
margin err: model 27.4 · mkt 33.5 · closer
Model
pred Ohio State 14.3 · actual Ohio State 23
winner Ohio State
ATS vs close
leaned Ohio State -10.5Cover ✓
margin err: model 8.7 · mkt 12.5 · closer
Model
pred Michigan State 6.7 · actual Michigan State 7
winner Michigan State
ATS vs close
leaned Purdue +14.0Cover ✓
margin err: model 0.3 · mkt 7.0 · closer
Illinois @ RutgersFinal 3831
Model
pred Rutgers 2.0 · actual Illinois 7
winner Rutgers
ATS vs close
leaned Illinois +2.3Cover ✓
margin err: model 9.0 · mkt 9.3 · closer
Model
pred Wisconsin 0.2 · actual Nebraska 19
winner Wisconsin
ATS vs close
leaned Wisconsin +1.5Miss ✗
margin err: model 19.2 · mkt 17.5 · mkt closer
Iowa @ MarylandFinal 2913
Model
pred Iowa 2.7 · actual Iowa 16
winner Iowa
ATS vs close
leaned Maryland +4.0Miss ✗
margin err: model 13.3 · mkt 12.0 · mkt closer
USC @ UCLAFinal 1913
Model
pred USC 5.6 · actual USC 6
winner USC
ATS vs close
leaned USC -4.5Cover ✓
margin err: model 0.4 · mkt 1.5 · closer
Model
pred Penn State 18.4 · actual Penn State 1
winner Penn State
ATS vs close
leaned Penn State -11.0Miss ✗
margin err: model 17.4 · mkt 10.0 · mkt 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.