CFB Betting Edge

2024 · Week 6 · SEC · backtest — what the model predicted vs what happened, and vs the market
Week 6 backtest · SEC · 6 games — what the model predicted vs what happened
Straight up
2–433%
ATS vs close
2–433%
Model margin MAE
19.8
Market margin MAE
17.4
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Auburn @ GeorgiaFinal 1331
Model
pred Georgia 16.0 · actual Georgia 18
winner Georgia
ATS vs close
leaned Auburn +21.0Cover ✓
margin err: model 2.0 · mkt 3.0 · closer
UCF @ FloridaFinal 1324
Model
pred UCF 3.3 · actual Florida 11
winner UCF
ATS vs close
leaned UCF -1.0Miss ✗
margin err: model 14.3 · mkt 12.0 · mkt closer
Model
pred Missouri 6.2 · actual Texas A&M 31
winner Missouri
ATS vs close
leaned Missouri +2.5Miss ✗
margin err: model 37.2 · mkt 28.5 · mkt closer
Model
pred Tennessee 9.0 · actual Arkansas 5
winner Tennessee
ATS vs close
leaned Arkansas +14.0Cover ✓
margin err: model 14.0 · mkt 19.0 · closer
Model
pred Ole Miss 9.7 · actual Ole Miss 24
winner Ole Miss
ATS vs close
leaned South Carolina +10.0Miss ✗
margin err: model 14.3 · mkt 14.0 · mkt closer
Model
pred Alabama 32.1 · actual Vanderbilt 5
winner Alabama
ATS vs close
leaned Alabama -23.0Miss ✗
margin err: model 37.1 · mkt 28.0 · 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.