CFB Betting Edge

2024 · Week 4 · Sun Belt · backtest — what the model predicted vs what happened, and vs the market
Week 4 backtest · Sun Belt · 9 games — what the model predicted vs what happened
Straight up
5–456%
ATS vs close
3–633%
Model margin MAE
21.9
Market margin MAE
18.1
→ 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 @ TexasFinal 351
Model
pred Texas 36.7 · actual Texas 48
winner Texas
ATS vs close
leaned UL Monroe +43.5Miss ✗
margin err: model 11.3 · mkt 4.5 · mkt closer
Model
pred Ohio State 34.7 · actual Ohio State 35
winner Ohio State
ATS vs close
leaned Marshall +39.0Cover ✓
margin err: model 0.3 · mkt 4.0 · closer
Model
pred Ole Miss 30.5 · actual Ole Miss 39
winner Ole Miss
ATS vs close
leaned Georgia Southern +35.0Miss ✗
margin err: model 8.5 · mkt 4.0 · mkt closer
Model
pred Iowa State 15.5 · actual Iowa State 45
winner Iowa State
ATS vs close
leaned Arkansas State +20.5Miss ✗
margin err: model 29.5 · mkt 24.5 · mkt closer
Model
pred North Carolina 14.6 · actual James Madison 20
winner North Carolina
ATS vs close
leaned North Carolina -11.0Miss ✗
margin err: model 34.6 · mkt 31.0 · mkt closer
Model
pred Coastal Carolina 12.5 · actual Virginia 19
winner Coastal Carolina
ATS vs close
leaned Coastal Carolina +3.5Miss ✗
margin err: model 31.5 · mkt 15.5 · mkt closer
Tulane @ LouisianaFinal 4133
Model
pred Louisiana 11.7 · actual Tulane 8
winner Louisiana
ATS vs close
leaned Louisiana +1.5Miss ✗
margin err: model 19.7 · mkt 6.5 · mkt closer
Model
pred Jacksonville State 10.4 · actual Jacksonville State 37
winner Jacksonville State
ATS vs close
leaned Jacksonville State -6.0Cover ✓
margin err: model 26.6 · mkt 31.0 · closer
Model
pred App State 0.8 · actual South Alabama 34
winner App State
ATS vs close
leaned South Alabama +7.5Cover ✓
margin err: model 34.8 · mkt 41.5 · 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.