CFB Betting Edge

2025 · Week 6 · SEC · backtest — what the model predicted vs what happened, and vs the market
Week 6 backtest · SEC · 5 games — what the model predicted vs what happened
Straight up
4–180%
ATS vs close
1–420%
Model margin MAE
8.5
Market margin MAE
4.7
→ 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 Oklahoma 47.4 · actual Oklahoma 44
winner Oklahoma
ATS vs close
leaned Oklahoma -46.5Miss ✗
margin err: model 3.4 · mkt 2.5 · mkt closer
Model
pred Texas A&M 20.4 · actual Texas A&M 22
winner Texas A&M
ATS vs close
leaned Texas A&M -17.5Cover ✓
margin err: model 1.6 · mkt 4.5 · closer
Kentucky @ GeorgiaFinal 1435
Model
pred Georgia 16.1 · actual Georgia 21
winner Georgia
ATS vs close
leaned Kentucky +19.5Miss ✗
margin err: model 4.9 · mkt 1.5 · mkt closer
Model
pred Alabama 2.7 · actual Alabama 16
winner Alabama
ATS vs close
leaned Vanderbilt +13.5Miss ✗
margin err: model 13.3 · mkt 2.5 · mkt closer
Texas @ FloridaFinal 2129
Model
pred Texas 11.5 · actual Florida 8
winner Texas
ATS vs close
leaned Texas -4.5Miss ✗
margin err: model 19.5 · mkt 12.5 · 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.