CFB Betting Edge

2024 · Week 11 · American Athletic · backtest — what the model predicted vs what happened, and vs the market
Week 11 backtest · American Athletic · 6 games — what the model predicted vs what happened
Straight up
5–183%
ATS vs close
2–3 · 1P40%
Model margin MAE
14.5
Market margin MAE
11.6
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Temple @ TulaneFinal 652
Model
pred Tulane 24.9 · actual Tulane 46
winner Tulane
ATS vs close
leaned Temple +25.5Miss ✗
margin err: model 21.1 · mkt 20.5 · mkt closer
Rice @ MemphisFinal 2027
Model
pred Memphis 14.5 · actual Memphis 7
winner Memphis
ATS vs close
leaned Memphis -7.0Push
margin err: model 7.5 · mkt 0.0 · mkt closer
Model
pred East Carolina 9.6 · actual East Carolina 35
winner East Carolina
ATS vs close
leaned East Carolina -7.5Cover ✓
margin err: model 25.4 · mkt 27.5 · closer
Model
pred South Florida 7.1 · actual Navy 21
winner South Florida
ATS vs close
leaned South Florida +4.5Miss ✗
margin err: model 28.1 · mkt 16.5 · mkt closer
UConn @ UABFinal 3123
Model
pred UConn 4.1 · actual UConn 8
winner UConn
ATS vs close
leaned UAB +7.5Miss ✗
margin err: model 3.9 · mkt 0.5 · mkt closer
Army @ North TexasFinal 143
Model
pred Army 10.2 · actual Army 11
winner Army
ATS vs close
leaned Army -6.5Cover ✓
margin err: model 0.8 · mkt 4.5 · 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.