CFB Betting Edge

2024 · Week 5 · American Athletic · backtest — what the model predicted vs what happened, and vs the market
Week 5 backtest · American Athletic · 7 games — what the model predicted vs what happened
Straight up
5–271%
ATS vs close
5–271%
Model margin MAE
15.0
Market margin MAE
16.4
→ model's margins were closer than the market
Results — model read vs the final score + how the closing-line lean held up
Model
pred Memphis 24.2 · actual Memphis 17
winner Memphis
ATS vs close
leaned Middle Tennessee +27.0Cover ✓
margin err: model 7.2 · mkt 10.0 · closer
Tulsa @ North TexasFinal 2052
Model
pred North Texas 6.8 · actual North Texas 32
winner North Texas
ATS vs close
leaned Tulsa +7.0Miss ✗
margin err: model 25.2 · mkt 25.0 · mkt closer
Model
pred East Carolina 4.8 · actual East Carolina 10
winner East Carolina
ATS vs close
leaned East Carolina -2.0Cover ✓
margin err: model 5.2 · mkt 8.0 · closer
Model
pred Tulane 4.5 · actual Tulane 35
winner Tulane
ATS vs close
leaned Tulane -4.0Cover ✓
margin err: model 30.5 · mkt 31.0 · closer
Charlotte @ RiceFinal 2120
Model
pred Rice 3.8 · actual Charlotte 1
winner Rice
ATS vs close
leaned Charlotte +4.0Cover ✓
margin err: model 4.8 · mkt 5.0 · closer
Navy @ UABFinal 4118
Model
pred UAB 0.3 · actual Navy 23
winner UAB
ATS vs close
leaned UAB +4.5Miss ✗
margin err: model 23.3 · mkt 18.5 · mkt closer
Army @ TempleFinal 4214
Model
pred Army 19.0 · actual Army 28
winner Army
ATS vs close
leaned Army -11.0Cover ✓
margin err: model 9.0 · mkt 17.0 · 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.