CFB Betting Edge

2025 · Week 13 · Sun Belt · backtest — what the model predicted vs what happened, and vs the market
Week 13 backtest · Sun Belt · 8 games — what the model predicted vs what happened
Straight up
6–275%
ATS vs close
3–538%
Model margin MAE
13.1
Market margin MAE
10.6
→ 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 Texas State 26.8 · actual Texas State 17
winner Texas State
ATS vs close
leaned Texas State -20.5Miss ✗
margin err: model 9.8 · mkt 3.5 · mkt closer
Model
pred South Carolina 17.6 · actual South Carolina 44
winner South Carolina
ATS vs close
leaned Coastal Carolina +24.0Miss ✗
margin err: model 26.4 · mkt 20.0 · mkt closer
Model
pred James Madison 16.0 · actual James Madison 4
winner James Madison
ATS vs close
leaned James Madison -15.5Miss ✗
margin err: model 12.0 · mkt 11.5 · mkt closer
Model
pred Troy 14.7 · actual Troy 12
winner Troy
ATS vs close
leaned Troy -9.5Cover ✓
margin err: model 2.7 · mkt 2.5 · mkt closer
Model
pred Old Dominion 0.6 · actual Old Dominion 35
winner Old Dominion
ATS vs close
leaned Georgia Southern +10.0Miss ✗
margin err: model 34.4 · mkt 25.0 · mkt closer
Model
pred Southern Miss 1.2 · actual South Alabama 7
winner Southern Miss
ATS vs close
leaned South Alabama +2.5Cover ✓
margin err: model 8.2 · mkt 9.5 · closer
Model
pred Louisiana 1.3 · actual Louisiana 4
winner Louisiana
ATS vs close
leaned Louisiana +2.5Cover ✓
margin err: model 2.7 · mkt 6.5 · closer
Model
pred Marshall 6.5 · actual App State 2
winner Marshall
ATS vs close
leaned Marshall -4.0Miss ✗
margin err: model 8.5 · mkt 6.0 · 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.