CFB Betting Edge

2024 · Week 9 · American Athletic · backtest — what the model predicted vs what happened, and vs the market
Week 9 backtest · American Athletic · 6 games — what the model predicted vs what happened
Straight up
5–183%
ATS vs close
4–267%
Model margin MAE
10.8
Market margin MAE
10.0
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Charlotte @ MemphisFinal 2833
Model
pred Memphis 16.8 · actual Memphis 5
winner Memphis
ATS vs close
leaned Charlotte +17.0Cover ✓
margin err: model 11.8 · mkt 12.0 · closer
Model
pred East Carolina 10.1 · actual East Carolina 22
winner East Carolina
ATS vs close
leaned East Carolina -8.5Cover ✓
margin err: model 11.9 · mkt 13.5 · closer
Rice @ UConnFinal 1017
Model
pred UConn 4.8 · actual UConn 7
winner UConn
ATS vs close
leaned Rice +6.5Miss ✗
margin err: model 2.2 · mkt 0.5 · mkt closer
UTSA @ TulsaFinal 4546
Model
pred UTSA 5.1 · actual Tulsa 1
winner UTSA
ATS vs close
leaned Tulsa +9.5Cover ✓
margin err: model 6.1 · mkt 10.5 · closer
Notre Dame @ NavyFinal 5114
Model
pred Notre Dame 12.2 · actual Notre Dame 37
winner Notre Dame
ATS vs close
leaned Navy +14.0Miss ✗
margin err: model 24.8 · mkt 23.0 · mkt closer
Model
pred Tulane 16.3 · actual Tulane 8
winner Tulane
ATS vs close
leaned Tulane -7.5Cover ✓
margin err: model 8.3 · mkt 0.5 · 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.