CFB Betting Edge

2024 · Week 4 · Mid-American · backtest — what the model predicted vs what happened, and vs the market
Week 4 backtest · Mid-American · 8 games — what the model predicted vs what happened
Straight up
6–275%
ATS vs close
3–538%
Model margin MAE
12.5
Market margin MAE
10.4
→ 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 Penn State 48.6 · actual Penn State 56
winner Penn State
ATS vs close
leaned Kent State +49.0Miss ✗
margin err: model 7.4 · mkt 7.0 · mkt closer
Model
pred Notre Dame 32.6 · actual Notre Dame 25
winner Notre Dame
ATS vs close
leaned Notre Dame -27.5Miss ✗
margin err: model 7.6 · mkt 2.5 · mkt closer
Model
pred Texas A&M 27.9 · actual Texas A&M 6
winner Texas A&M
ATS vs close
leaned Texas A&M -21.0Miss ✗
margin err: model 21.9 · mkt 15.0 · mkt closer
Model
pred South Carolina 27.1 · actual South Carolina 43
winner South Carolina
ATS vs close
leaned South Carolina -25.0Cover ✓
margin err: model 15.9 · mkt 18.0 · closer
Ohio @ KentuckyFinal 641
Model
pred Kentucky 19.0 · actual Kentucky 35
winner Kentucky
ATS vs close
leaned Ohio +21.5Miss ✗
margin err: model 16.0 · mkt 13.5 · mkt closer
Model
pred Northern Illinois 12.3 · actual Buffalo 3
winner Northern Illinois
ATS vs close
leaned Buffalo +13.0Cover ✓
margin err: model 15.3 · mkt 16.0 · closer
Model
pred Central Michigan 2.4 · actual Central Michigan 3
winner Central Michigan
ATS vs close
leaned Ball State +6.5Cover ✓
margin err: model 0.6 · mkt 3.5 · closer
Model
pred Toledo 10.6 · actual Western Kentucky 5
winner Toledo
ATS vs close
leaned Toledo -2.5Miss ✗
margin err: model 15.6 · mkt 7.5 · 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.