CFB Betting Edge

2025 · Week 11 · SEC · backtest — what the model predicted vs what happened, and vs the market
Week 11 backtest · SEC · 5 games — what the model predicted vs what happened
Straight up
4–180%
ATS vs close
3–175%
Model margin MAE
12.7
Market margin MAE
12.4
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
LSU @ AlabamaFinal 920
Model
pred Alabama 14.0 · actual Alabama 11
winner Alabama
ATS vs close
leaned Alabama -10.0Cover ✓
margin err: model 3.0 · mkt 1.0 · mkt closer
Auburn @ VanderbiltFinal 3845
Model
pred Vanderbilt 12.5 · actual Vanderbilt 7
winner Vanderbilt
ATS vs close
leaned Vanderbilt -6.0Cover ✓
margin err: model 5.5 · mkt 1.0 · mkt closer
Florida @ KentuckyFinal 738
Model
pred Florida 4.5 · actual Kentucky 31
winner Florida
ATS vs close
model matched the close — no lean
margin err: model 35.5 · mkt 35.5 · tie
Model
pred Texas A&M 5.0 · actual Texas A&M 21
winner Texas A&M
ATS vs close
leaned Missouri +7.0Miss ✗
margin err: model 16.0 · mkt 14.0 · mkt closer
Model
pred Georgia 16.5 · actual Georgia 20
winner Georgia
ATS vs close
leaned Georgia -9.5Cover ✓
margin err: model 3.5 · mkt 10.5 · 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.