CFB Betting Edge

2025 · Week 7 · SEC · backtest — what the model predicted vs what happened, and vs the market
Week 7 backtest · SEC · 7 games — what the model predicted vs what happened
Straight up
5–271%
ATS vs close
3–3 · 1P50%
Model margin MAE
9.6
Market margin MAE
9.8
→ model's margins were closer than the market
Results — model read vs the final score + how the closing-line lean held up
Model
pred Ole Miss 23.6 · actual Ole Miss 3
winner Ole Miss
ATS vs close
leaned Washington State +33.0Cover ✓
margin err: model 20.6 · mkt 30.0 · closer
Florida @ Texas A&MFinal 1734
Model
pred Texas A&M 16.4 · actual Texas A&M 17
winner Texas A&M
ATS vs close
leaned Texas A&M -7.0Cover ✓
margin err: model 0.6 · mkt 10.0 · closer
Model
pred Tennessee 14.0 · actual Tennessee 3
winner Tennessee
ATS vs close
leaned Tennessee -10.0Miss ✗
margin err: model 11.0 · mkt 7.0 · mkt closer
Model
pred LSU 5.1 · actual LSU 10
winner LSU
ATS vs close
leaned South Carolina +8.5Miss ✗
margin err: model 4.9 · mkt 1.5 · mkt closer
Alabama @ MissouriFinal 2724
Model
pred Missouri 3.4 · actual Alabama 3
winner Missouri
ATS vs close
leaned Missouri +3.0Push
margin err: model 6.4 · mkt 0.0 · mkt closer
Oklahoma @ TexasFinal 623
Model
pred Oklahoma 4.0 · actual Texas 17
winner Oklahoma
ATS vs close
leaned Oklahoma +2.5Miss ✗
margin err: model 21.0 · mkt 14.5 · mkt closer
Georgia @ AuburnFinal 2010
Model
pred Georgia 7.0 · actual Georgia 10
winner Georgia
ATS vs close
leaned Georgia -4.5Cover ✓
margin err: model 3.0 · mkt 5.5 · 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.