CFB Betting Edge

2025 · Week 4 · SEC · backtest — what the model predicted vs what happened, and vs the market
Week 4 backtest · SEC · 9 games — what the model predicted vs what happened
Straight up
8–189%
ATS vs close
5–456%
Model margin MAE
10.4
Market margin MAE
10.1
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Model
pred Texas 34.7 · actual Texas 55
winner Texas
ATS vs close
leaned Sam Houston +39.5Miss ✗
margin err: model 20.3 · mkt 15.5 · mkt closer
Model
pred Vanderbilt 32.3 · actual Vanderbilt 49
winner Vanderbilt
ATS vs close
leaned Vanderbilt -27.5Cover ✓
margin err: model 16.7 · mkt 21.5 · closer
UAB @ TennesseeFinal 2456
Model
pred Tennessee 28.6 · actual Tennessee 32
winner Tennessee
ATS vs close
leaned UAB +39.0Cover ✓
margin err: model 3.4 · mkt 7.0 · closer
Tulane @ Ole MissFinal 1045
Model
pred Ole Miss 15.2 · actual Ole Miss 35
winner Ole Miss
ATS vs close
leaned Ole Miss -12.5Cover ✓
margin err: model 19.8 · mkt 22.5 · closer
Model
pred Missouri 13.8 · actual Missouri 9
winner Missouri
ATS vs close
leaned Missouri -10.0Miss ✗
margin err: model 4.8 · mkt 1.0 · mkt closer
Model
pred Mississippi State 11.7 · actual Mississippi State 28
winner Mississippi State
ATS vs close
leaned Northern Illinois +24.0Miss ✗
margin err: model 16.3 · mkt 4.0 · mkt closer
Florida @ MiamiFinal 726
Model
pred Miami 10.7 · actual Miami 19
winner Miami
ATS vs close
leaned Miami -8.5Cover ✓
margin err: model 8.3 · mkt 10.5 · closer
Auburn @ OklahomaFinal 1724
Model
pred Oklahoma 4.5 · actual Oklahoma 7
winner Oklahoma
ATS vs close
leaned Auburn +6.5Miss ✗
margin err: model 2.5 · mkt 0.5 · mkt closer
Arkansas @ MemphisFinal 3132
Model
pred Arkansas 0.1 · actual Memphis 1
winner Arkansas
ATS vs close
leaned Memphis +7.0Cover ✓
margin err: model 1.1 · mkt 8.0 · 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.