CFB Betting Edge

2024 · Week 7 · Conference USA · backtest — what the model predicted vs what happened, and vs the market
Week 7 backtest · Conference USA · 4 games — what the model predicted vs what happened
Straight up
4–0100%
ATS vs close
0–40%
Model margin MAE
19.6
Market margin MAE
14.6
→ 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 Liberty 18.8 · actual Liberty 7
winner Liberty
ATS vs close
leaned Liberty -15.5Miss ✗
margin err: model 11.8 · mkt 8.5 · mkt closer
Model
pred Western Kentucky 13.3 · actual Western Kentucky 27
winner Western Kentucky
ATS vs close
leaned UTEP +19.0Miss ✗
margin err: model 13.7 · mkt 8.0 · mkt closer
Model
pred Jacksonville State 11.0 · actual Jacksonville State 41
winner Jacksonville State
ATS vs close
leaned New Mexico State +21.0Miss ✗
margin err: model 30.0 · mkt 20.0 · mkt closer
Model
pred Louisiana Tech 4.2 · actual Louisiana Tech 27
winner Louisiana Tech
ATS vs close
leaned Middle Tennessee +5.0Miss ✗
margin err: model 22.8 · mkt 22.0 · 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.