CFB Betting Edge

2024 · Week 10 · SEC · backtest — what the model predicted vs what happened, and vs the market
Week 10 backtest · SEC · 6 games — what the model predicted vs what happened
Straight up
4–267%
ATS vs close
3–350%
Model margin MAE
14.6
Market margin MAE
13.7
→ 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 17.3 · actual Tennessee 10
winner Tennessee
ATS vs close
leaned Kentucky +17.5Cover ✓
margin err: model 7.3 · mkt 7.5 · closer
Model
pred Mississippi State 15.0 · actual Mississippi State 25
winner Mississippi State
ATS vs close
leaned Massachusetts +19.5Miss ✗
margin err: model 10.0 · mkt 5.5 · mkt closer
Florida @ GeorgiaFinal 2034
Model
pred Georgia 13.1 · actual Georgia 14
winner Georgia
ATS vs close
leaned Florida +14.5Cover ✓
margin err: model 0.9 · mkt 0.5 · mkt closer
Model
pred Auburn 10.8 · actual Vanderbilt 10
winner Auburn
ATS vs close
leaned Auburn -7.5Miss ✗
margin err: model 20.8 · mkt 17.5 · mkt closer
Model
pred Texas A&M 6.7 · actual South Carolina 24
winner Texas A&M
ATS vs close
leaned Texas A&M -3.0Miss ✗
margin err: model 30.7 · mkt 27.0 · mkt closer
Ole Miss @ ArkansasFinal 6331
Model
pred Ole Miss 13.9 · actual Ole Miss 32
winner Ole Miss
ATS vs close
leaned Ole Miss -8.0Cover ✓
margin err: model 18.1 · mkt 24.0 · 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.