CFB Betting Edge

2024 · Week 5 · Conference USA · backtest — what the model predicted vs what happened, and vs the market
Week 5 backtest · Conference USA · 6 games — what the model predicted vs what happened
Straight up
3–260%
ATS vs close
3–260%
Model margin MAE
8.4
Market margin MAE
7.6
→ 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 Memphis 24.2 · actual Memphis 17
winner Memphis
ATS vs close
leaned Middle Tennessee +27.0Cover ✓
margin err: model 7.2 · mkt 10.0 · closer
Model
pred Boston College 13.6 · actual Boston College 1
winner Boston College
ATS vs close
leaned Boston College -7.5Miss ✗
margin err: model 12.6 · mkt 6.5 · mkt closer
Model
pred Florida International 6.3 · actual Florida International 7
winner Florida International
ATS vs close
leaned Florida International +2.0Cover ✓
margin err: model 0.7 · mkt 9.0 · closer
Model
pred New Mexico State 2.9 · actual New Mexico 10
winner New Mexico State
ATS vs close
leaned New Mexico State +9.5Miss ✗
margin err: model 12.9 · mkt 0.5 · mkt closer
Model
pred Liberty 3.7 · actual tie
winner Liberty · tie
ATS vs close
no closing line
Model
pred Texas State 7.5 · actual Sam Houston 1
winner Texas State
ATS vs close
leaned Sam Houston +11.0Cover ✓
margin err: model 8.5 · mkt 12.0 · 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.