CFB Betting Edge

2025 · Week 12 · SEC · backtest — what the model predicted vs what happened, and vs the market
Week 12 backtest · SEC · 7 games — what the model predicted vs what happened
Straight up
6–186%
ATS vs close
3–443%
Model margin MAE
10.8
Market margin MAE
10.3
→ 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 Tennessee 31.3 · actual Tennessee 33
winner Tennessee
ATS vs close
leaned New Mexico State +41.5Cover ✓
margin err: model 1.7 · mkt 8.5 · closer
Model
pred Texas A&M 15.9 · actual Texas A&M 1
winner Texas A&M
ATS vs close
leaned South Carolina +16.5Cover ✓
margin err: model 14.9 · mkt 15.5 · closer
Oklahoma @ AlabamaFinal 2321
Model
pred Alabama 9.5 · actual Oklahoma 2
winner Alabama
ATS vs close
leaned Alabama -6.5Miss ✗
margin err: model 11.5 · mkt 8.5 · mkt closer
Arkansas @ LSUFinal 2223
Model
pred LSU 8.1 · actual LSU 1
winner LSU
ATS vs close
leaned LSU -4.0Miss ✗
margin err: model 7.1 · mkt 3.0 · mkt closer
Florida @ Ole MissFinal 2434
Model
pred Ole Miss 7.6 · actual Ole Miss 10
winner Ole Miss
ATS vs close
leaned Florida +10.5Cover ✓
margin err: model 2.4 · mkt 0.5 · mkt closer
Model
pred Missouri 7.3 · actual Missouri 22
winner Missouri
ATS vs close
leaned Mississippi State +7.5Miss ✗
margin err: model 14.7 · mkt 14.5 · mkt closer
Texas @ GeorgiaFinal 1035
Model
pred Georgia 2.0 · actual Georgia 25
winner Georgia
ATS vs close
leaned Texas +3.5Miss ✗
margin err: model 23.0 · mkt 21.5 · 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.