CFB Betting Edge

2024 · Week 12 · Sun Belt · backtest — what the model predicted vs what happened, and vs the market
Week 12 backtest · Sun Belt · 7 games — what the model predicted vs what happened
Straight up
4–357%
ATS vs close
4–357%
Model margin MAE
11.8
Market margin MAE
10.9
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
UL Monroe @ AuburnFinal 1448
Model
pred Auburn 30.4 · actual Auburn 34
winner Auburn
ATS vs close
leaned Auburn -24.5Cover ✓
margin err: model 3.6 · mkt 9.5 · closer
Model
pred Texas State 18.0 · actual Texas State 55
winner Texas State
ATS vs close
leaned Southern Miss +27.5Miss ✗
margin err: model 37.0 · mkt 27.5 · mkt closer
Model
pred Louisiana 7.0 · actual South Alabama 2
winner Louisiana
ATS vs close
leaned Louisiana -6.5Miss ✗
margin err: model 9.0 · mkt 8.5 · mkt closer
Model
pred Georgia Southern 4.3 · actual Troy 8
winner Georgia Southern
ATS vs close
leaned Troy +7.0Cover ✓
margin err: model 12.3 · mkt 15.0 · closer
Model
pred Marshall 3.9 · actual Marshall 12
winner Marshall
ATS vs close
leaned Coastal Carolina +7.5Miss ✗
margin err: model 8.1 · mkt 4.5 · mkt closer
Model
pred Georgia State 0.4 · actual Arkansas State 7
winner Georgia State
ATS vs close
leaned Arkansas State +2.5Cover ✓
margin err: model 7.4 · mkt 9.5 · closer
Model
pred James Madison 8.0 · actual James Madison 3
winner James Madison
ATS vs close
leaned James Madison -1.5Cover ✓
margin err: model 5.0 · mkt 1.5 · 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.