CFB Betting Edge

2025 · Week 9 · SEC · backtest — what the model predicted vs what happened, and vs the market
Week 9 backtest · SEC · 7 games — what the model predicted vs what happened
Straight up
4–357%
ATS vs close
5–271%
Model margin MAE
9.8
Market margin MAE
10.3
→ model's margins were closer than the market
Results — model read vs the final score + how the closing-line lean held up
Model
pred Vanderbilt 4.6 · actual Vanderbilt 7
winner Vanderbilt
ATS vs close
leaned Vanderbilt -3.0Cover ✓
margin err: model 2.4 · mkt 4.0 · closer
Auburn @ ArkansasFinal 3324
Model
pred Arkansas 2.3 · actual Auburn 9
winner Arkansas
ATS vs close
leaned Auburn +2.5Cover ✓
margin err: model 11.3 · mkt 11.5 · closer
Ole Miss @ OklahomaFinal 3426
Model
pred Oklahoma 2.0 · actual Ole Miss 8
winner Oklahoma
ATS vs close
leaned Ole Miss +5.5Cover ✓
margin err: model 10.0 · mkt 13.5 · closer
Texas A&M @ LSUFinal 4925
Model
pred LSU 0.3 · actual Texas A&M 24
winner LSU
ATS vs close
leaned LSU +1.5Miss ✗
margin err: model 24.3 · mkt 22.5 · mkt closer
Model
pred Alabama 8.4 · actual Alabama 7
winner Alabama
ATS vs close
leaned South Carolina +11.5Cover ✓
margin err: model 1.4 · mkt 4.5 · closer
Model
pred Tennessee 9.9 · actual Tennessee 22
winner Tennessee
ATS vs close
leaned Tennessee -7.5Cover ✓
margin err: model 12.1 · mkt 14.5 · closer
Model
pred Texas 13.9 · actual Texas 7
winner Texas
ATS vs close
leaned Texas -8.5Miss ✗
margin err: model 6.9 · mkt 1.5 · 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.