CFB Betting Edge

2025 · Week 13 · American Athletic · backtest — what the model predicted vs what happened, and vs the market
Week 13 backtest · American Athletic · 7 games — what the model predicted vs what happened
Straight up
6–186%
ATS vs close
3–443%
Model margin MAE
17.0
Market margin MAE
14.1
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Model
pred Georgia 42.4 · actual Georgia 32
winner Georgia
ATS vs close
leaned Charlotte +42.5Cover ✓
margin err: model 10.4 · mkt 10.5 · closer
Tulsa @ ArmyFinal 2625
Model
pred Army 15.6 · actual Tulsa 1
winner Army
ATS vs close
leaned Army -10.0Miss ✗
margin err: model 16.6 · mkt 11.0 · mkt closer
Model
pred UTSA 2.2 · actual UTSA 34
winner UTSA
ATS vs close
leaned UTSA +2.0Cover ✓
margin err: model 31.8 · mkt 36.0 · closer
North Texas @ RiceFinal 5624
Model
pred North Texas 4.3 · actual North Texas 32
winner North Texas
ATS vs close
leaned Rice +18.5Miss ✗
margin err: model 27.7 · mkt 13.5 · mkt closer
Model
pred UConn 8.2 · actual UConn 3
winner UConn
ATS vs close
leaned UConn -6.0Miss ✗
margin err: model 5.2 · mkt 3.0 · mkt closer
Tulane @ TempleFinal 3713
Model
pred Tulane 12.9 · actual Tulane 24
winner Tulane
ATS vs close
leaned Tulane -7.5Cover ✓
margin err: model 11.1 · mkt 16.5 · closer
South Florida @ UABFinal 4818
Model
pred South Florida 13.7 · actual South Florida 30
winner South Florida
ATS vs close
leaned UAB +21.5Miss ✗
margin err: model 16.3 · mkt 8.5 · 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.