CFB Betting Edge

2024 · Week 10 · Sun Belt · backtest — what the model predicted vs what happened, and vs the market
Week 10 backtest · Sun Belt · 6 games — what the model predicted vs what happened
Straight up
3–350%
ATS vs close
2–3 · 1P40%
Model margin MAE
9.7
Market margin MAE
8.9
→ 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 Marshall 14.7 · actual Marshall 5
winner Marshall
ATS vs close
leaned Marshall -10.5Miss ✗
margin err: model 9.7 · mkt 5.5 · mkt closer
Model
pred South Alabama 9.8 · actual Georgia Southern 4
winner South Alabama
ATS vs close
leaned South Alabama -5.5Miss ✗
margin err: model 13.8 · mkt 9.5 · mkt closer
Model
pred Texas State 6.1 · actual Louisiana 6
winner Texas State
ATS vs close
leaned Texas State -4.0Miss ✗
margin err: model 12.1 · mkt 10.0 · mkt closer
Model
pred UConn 3.9 · actual UConn 7
winner UConn
ATS vs close
leaned Georgia State +7.0Push
margin err: model 3.1 · mkt 0.0 · mkt closer
Model
pred App State 3.4 · actual App State 8
winner App State
ATS vs close
leaned App State +2.5Cover ✓
margin err: model 4.6 · mkt 10.5 · closer
Model
pred Coastal Carolina 0.7 · actual Troy 14
winner Coastal Carolina
ATS vs close
leaned Troy +4.0Cover ✓
margin err: model 14.7 · mkt 18.0 · 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.