CFB Betting Edge

2024 · Week 1 · Mid-American · backtest — what the model predicted vs what happened, and vs the market
Week 1 backtest · Mid-American · 6 games — what the model predicted vs what happened
Straight up
5–183%
ATS vs close
6–0100%
Model margin MAE
7.5
Market margin MAE
7.1
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Akron @ Ohio StateFinal 652
Model
pred Ohio State 38.7 · actual Ohio State 46
winner Ohio State
ATS vs close
leaned Akron +49.5Cover ✓
margin err: model 7.3 · mkt 3.5 · mkt closer
Model
pred Pittsburgh 25.1 · actual Pittsburgh 31
winner Pittsburgh
ATS vs close
leaned Pittsburgh -23.5Cover ✓
margin err: model 5.9 · mkt 7.5 · closer
Model
pred Wisconsin 21.5 · actual Wisconsin 14
winner Wisconsin
ATS vs close
leaned Western Michigan +24.0Cover ✓
margin err: model 7.5 · mkt 10.0 · closer
Ohio @ SyracuseFinal 2238
Model
pred Syracuse 9.6 · actual Syracuse 16
winner Syracuse
ATS vs close
leaned Ohio +17.5Cover ✓
margin err: model 6.4 · mkt 1.5 · mkt closer
Model
pred Northwestern 3.8 · actual Northwestern 7
winner Northwestern
ATS vs close
leaned Northwestern -3.5Cover ✓
margin err: model 3.2 · mkt 3.5 · closer
Model
pred Massachusetts 0.8 · actual Eastern Michigan 14
winner Massachusetts
ATS vs close
leaned Eastern Michigan +2.5Cover ✓
margin err: model 14.8 · mkt 16.5 · 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.