CFB Betting Edge

2024 · Week 2 · American Athletic · backtest — what the model predicted vs what happened, and vs the market
Week 2 backtest · American Athletic · 10 games — what the model predicted vs what happened
Straight up
7–370%
ATS vs close
4–640%
Model margin MAE
15.2
Market margin MAE
13.3
→ 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 Alabama 30.5 · actual Alabama 26
winner Alabama
ATS vs close
leaned South Florida +31.0Cover ✓
margin err: model 4.5 · mkt 5.0 · closer
Model
pred North Carolina 27.5 · actual North Carolina 18
winner North Carolina
ATS vs close
leaned North Carolina -21.5Miss ✗
margin err: model 9.5 · mkt 3.5 · mkt closer
Temple @ NavyFinal 1138
Model
pred Navy 11.1 · actual Navy 27
winner Navy
ATS vs close
leaned Temple +11.5Miss ✗
margin err: model 15.9 · mkt 15.5 · mkt closer
Model
pred Arkansas State 8.0 · actual Arkansas State 4
winner Arkansas State
ATS vs close
leaned Tulsa +9.0Cover ✓
margin err: model 4.0 · mkt 5.0 · closer
Troy @ MemphisFinal 1738
Model
pred Memphis 7.9 · actual Memphis 21
winner Memphis
ATS vs close
leaned Troy +18.5Miss ✗
margin err: model 13.1 · mkt 2.5 · mkt closer
Model
pred Florida Atlantic 2.0 · actual Army 17
winner Florida Atlantic
ATS vs close
leaned Florida Atlantic -1.5Miss ✗
margin err: model 19.0 · mkt 18.5 · mkt closer
Model
pred East Carolina 2.7 · actual East Carolina 6
winner East Carolina
ATS vs close
leaned East Carolina +1.5Cover ✓
margin err: model 3.3 · mkt 7.5 · closer
UTSA @ Texas StateFinal 1049
Model
pred UTSA 4.1 · actual Texas State 39
winner UTSA
ATS vs close
leaned UTSA +2.5Miss ✗
margin err: model 43.1 · mkt 36.5 · mkt closer
Model
pred Kansas State 8.5 · actual Kansas State 7
winner Kansas State
ATS vs close
leaned Tulane +9.0Cover ✓
margin err: model 1.5 · mkt 2.0 · closer
UAB @ UL MonroeFinal 632
Model
pred UAB 12.0 · actual UL Monroe 26
winner UAB
ATS vs close
leaned UAB -11.0Miss ✗
margin err: model 38.0 · mkt 37.0 · 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.