CFB Betting Edge

2025 · 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
3–350%
ATS vs close
5–183%
Model margin MAE
6.0
Market margin MAE
7.1
→ 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 15.2 · actual Ole Miss 16
winner Ole Miss
ATS vs close
leaned Ole Miss -13.0Cover ✓
margin err: model 0.8 · mkt 3.0 · closer
Vanderbilt @ TexasFinal 3134
Model
pred Texas 7.5 · actual Texas 3
winner Texas
ATS vs close
leaned Texas -3.5Miss ✗
margin err: model 4.5 · mkt 0.5 · mkt closer
Kentucky @ AuburnFinal 103
Model
pred Auburn 7.0 · actual Kentucky 7
winner Auburn
ATS vs close
leaned Kentucky +11.5Cover ✓
margin err: model 14.0 · mkt 18.5 · closer
Model
pred Arkansas 3.3 · actual Mississippi State 3
winner Arkansas
ATS vs close
leaned Mississippi State +5.5Cover ✓
margin err: model 6.3 · mkt 8.5 · closer
Model
pred Tennessee 1.7 · actual Oklahoma 6
winner Tennessee
ATS vs close
leaned Oklahoma +3.0Cover ✓
margin err: model 7.7 · mkt 9.0 · closer
Georgia @ FloridaFinal 2420
Model
pred Georgia 6.9 · actual Georgia 4
winner Georgia
ATS vs close
leaned Florida +7.0Cover ✓
margin err: model 2.9 · mkt 3.0 · 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.