CFB Betting Edge

2024 · Week 6 · American Athletic · backtest — what the model predicted vs what happened, and vs the market
Week 6 backtest · American Athletic · 5 games — what the model predicted vs what happened
Straight up
4–180%
ATS vs close
1–420%
Model margin MAE
27.7
Market margin MAE
25.2
→ 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 @ UConnFinal 2029
Model
pred UConn 20.5 · actual UConn 9
winner UConn
ATS vs close
leaned UConn -17.5Miss ✗
margin err: model 11.5 · mkt 8.5 · mkt closer
Navy @ Air ForceFinal 347
Model
pred Navy 4.2 · actual Navy 27
winner Navy
ATS vs close
leaned Air Force +10.0Miss ✗
margin err: model 22.8 · mkt 17.0 · mkt closer
Model
pred East Carolina 7.8 · actual Charlotte 31
winner East Carolina
ATS vs close
leaned Charlotte +9.5Cover ✓
margin err: model 38.8 · mkt 40.5 · closer
Army @ TulsaFinal 497
Model
pred Army 11.8 · actual Army 42
winner Army
ATS vs close
leaned Tulsa +13.5Miss ✗
margin err: model 30.2 · mkt 28.5 · mkt closer
Tulane @ UABFinal 7120
Model
pred Tulane 15.8 · actual Tulane 51
winner Tulane
ATS vs close
leaned UAB +19.5Miss ✗
margin err: model 35.2 · mkt 31.5 · 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.