CFB Betting Edge

2024 · Week 2 · Conference USA · backtest — what the model predicted vs what happened, and vs the market
Week 2 backtest · Conference USA · 6 games — what the model predicted vs what happened
Straight up
4–267%
ATS vs close
3–350%
Model margin MAE
19.8
Market margin MAE
14.5
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Sam Houston @ UCFFinal 1445
Model
pred UCF 27.8 · actual UCF 31
winner UCF
ATS vs close
leaned UCF -21.5Cover ✓
margin err: model 3.2 · mkt 9.5 · closer
Model
pred Ole Miss 24.6 · actual Ole Miss 49
winner Ole Miss
ATS vs close
leaned Middle Tennessee +42.5Miss ✗
margin err: model 24.4 · mkt 6.5 · mkt closer
Model
pred Louisville 16.8 · actual Louisville 35
winner Louisville
ATS vs close
leaned Jacksonville State +29.0Miss ✗
margin err: model 18.2 · mkt 6.0 · mkt closer
Model
pred Kennesaw State 5.0 · actual Louisiana 24
winner Kennesaw State
ATS vs close
leaned Kennesaw State +14.5Miss ✗
margin err: model 29.0 · mkt 9.5 · mkt closer
Model
pred Central Michigan 3.1 · actual Florida International 36
winner Central Michigan
ATS vs close
leaned Florida International +3.5Cover ✓
margin err: model 39.1 · mkt 39.5 · closer
Model
pred Liberty 10.6 · actual Liberty 6
winner Liberty
ATS vs close
leaned New Mexico State +22.0Cover ✓
margin err: model 4.6 · mkt 16.0 · 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.