CFB Betting Edge

2024 · Week 8 · American Athletic · backtest — what the model predicted vs what happened, and vs the market
Week 8 backtest · American Athletic · 7 games — what the model predicted vs what happened
Straight up
6–186%
ATS vs close
3–443%
Model margin MAE
8.3
Market margin MAE
7.0
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Rice @ TulaneFinal 1024
Model
pred Tulane 20.5 · actual Tulane 14
winner Tulane
ATS vs close
leaned Rice +21.5Cover ✓
margin err: model 6.5 · mkt 7.5 · closer
Model
pred Memphis 15.0 · actual Memphis 8
winner Memphis
ATS vs close
leaned Memphis -10.5Miss ✗
margin err: model 7.0 · mkt 2.5 · mkt closer
Charlotte @ NavyFinal 1751
Model
pred Navy 14.5 · actual Navy 34
winner Navy
ATS vs close
leaned Charlotte +16.5Miss ✗
margin err: model 19.5 · mkt 17.5 · mkt closer
Model
pred Army 13.8 · actual Army 17
winner Army
ATS vs close
leaned East Carolina +17.5Cover ✓
margin err: model 3.2 · mkt 0.5 · mkt closer
UAB @ South FloridaFinal 2535
Model
pred South Florida 11.1 · actual South Florida 10
winner South Florida
ATS vs close
leaned UAB +14.0Cover ✓
margin err: model 1.1 · mkt 4.0 · closer
Model
pred UTSA 3.1 · actual UTSA 14
winner UTSA
ATS vs close
leaned Florida Atlantic +4.0Miss ✗
margin err: model 10.9 · mkt 10.0 · mkt closer
Tulsa @ TempleFinal 1020
Model
pred Tulsa 0.2 · actual Temple 10
winner Tulsa
ATS vs close
leaned Tulsa +3.0Miss ✗
margin err: model 10.2 · mkt 7.0 · 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.