CFB Betting Edge

2024 · Week 10 · Mountain West · backtest — what the model predicted vs what happened, and vs the market
Week 10 backtest · Mountain West · 5 games — what the model predicted vs what happened
Straight up
3–260%
ATS vs close
1–420%
Model margin MAE
10.6
Market margin MAE
9.7
→ 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 Boise State 21.2 · actual Boise State 32
winner Boise State
ATS vs close
leaned San Diego State +24.5Miss ✗
margin err: model 10.8 · mkt 7.5 · mkt closer
Air Force @ ArmyFinal 320
Model
pred Army 19.2 · actual Army 17
winner Army
ATS vs close
leaned Army -18.0Miss ✗
margin err: model 2.2 · mkt 1.0 · mkt closer
Model
pred Fresno State 14.1 · actual Hawai'i 1
winner Fresno State
ATS vs close
leaned Fresno State -12.5Miss ✗
margin err: model 15.1 · mkt 13.5 · mkt closer
Model
pred New Mexico 7.9 · actual Wyoming 4
winner New Mexico
ATS vs close
leaned New Mexico -7.5Miss ✗
margin err: model 11.9 · mkt 11.5 · mkt closer
Model
pred Colorado State 4.1 · actual Colorado State 17
winner Colorado State
ATS vs close
leaned Colorado State -2.0Cover ✓
margin err: model 12.9 · mkt 15.0 · 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.