CFB Betting Edge

2024 · Week 1 · Conference USA · backtest — what the model predicted vs what happened, and vs the market
Week 1 backtest · Conference USA · 6 games — what the model predicted vs what happened
Straight up
4–267%
ATS vs close
3–350%
Model margin MAE
20.4
Market margin MAE
18.2
→ 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 Alabama 35.2 · actual Alabama 63
winner Alabama
ATS vs close
leaned Alabama -34.0Cover ✓
margin err: model 27.8 · mkt 29.0 · closer
Model
pred UTSA 27.1 · actual UTSA 12
winner UTSA
ATS vs close
leaned UTSA -24.0Miss ✗
margin err: model 15.1 · mkt 12.0 · mkt closer
UTEP @ NebraskaFinal 740
Model
pred Nebraska 22.7 · actual Nebraska 33
winner Nebraska
ATS vs close
leaned UTEP +27.5Miss ✗
margin err: model 10.3 · mkt 5.5 · mkt closer
Model
pred Indiana 17.9 · actual Indiana 24
winner Indiana
ATS vs close
leaned Florida International +25.5Cover ✓
margin err: model 6.1 · mkt 1.5 · mkt closer
Sam Houston @ RiceFinal 3414
Model
pred Rice 8.9 · actual Sam Houston 20
winner Rice
ATS vs close
leaned Sam Houston +9.5Cover ✓
margin err: model 28.9 · mkt 29.5 · closer
Model
pred Jacksonville State 6.1 · actual Coastal Carolina 28
winner Jacksonville State
ATS vs close
leaned Jacksonville State -3.5Miss ✗
margin err: model 34.1 · mkt 31.5 · 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.