CFB Betting Edge

2024 · Week 5 · SEC · backtest — what the model predicted vs what happened, and vs the market
Week 5 backtest · SEC · 6 games — what the model predicted vs what happened
Straight up
5–183%
ATS vs close
4–267%
Model margin MAE
8.3
Market margin MAE
10.6
→ model's margins were closer than the market
Results — model read vs the final score + how the closing-line lean held up
Model
pred Texas 28.3 · actual Texas 22
winner Texas
ATS vs close
leaned Mississippi State +37.0Cover ✓
margin err: model 6.3 · mkt 15.0 · closer
Kentucky @ Ole MissFinal 2017
Model
pred Ole Miss 24.3 · actual Kentucky 3
winner Ole Miss
ATS vs close
leaned Ole Miss -15.0Miss ✗
margin err: model 27.3 · mkt 18.0 · mkt closer
South Alabama @ LSUFinal 1042
Model
pred LSU 22.3 · actual LSU 32
winner LSU
ATS vs close
leaned LSU -21.0Cover ✓
margin err: model 9.7 · mkt 11.0 · closer
Georgia @ AlabamaFinal 3441
Model
pred Alabama 9.6 · actual Alabama 7
winner Alabama
ATS vs close
leaned Alabama +2.0Cover ✓
margin err: model 2.6 · mkt 9.0 · closer
Model
pred Texas A&M 7.9 · actual Texas A&M 4
winner Texas A&M
ATS vs close
leaned Texas A&M -6.5Miss ✗
margin err: model 3.9 · mkt 2.5 · mkt closer
Oklahoma @ AuburnFinal 2721
Model
pred Oklahoma 6.3 · actual Oklahoma 6
winner Oklahoma
ATS vs close
leaned Oklahoma +2.0Cover ✓
margin err: model 0.3 · mkt 8.0 · 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.