CFB Betting Edge

2025 · Week 7 · Mountain West · backtest — what the model predicted vs what happened, and vs the market
Week 7 backtest · Mountain West · 6 games — what the model predicted vs what happened
Straight up
4–267%
ATS vs close
5–183%
Model margin MAE
16.8
Market margin MAE
15.8
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Air Force @ UNLVFinal 4851
Model
pred UNLV 25.8 · actual UNLV 3
winner UNLV
ATS vs close
leaned UNLV -7.0Miss ✗
margin err: model 22.8 · mkt 4.0 · mkt closer
Model
pred Boise State 15.6 · actual Boise State 16
winner Boise State
ATS vs close
leaned Boise State -14.5Cover ✓
margin err: model 0.4 · mkt 1.5 · closer
Model
pred Wyoming 2.4 · actual Wyoming 7
winner Wyoming
ATS vs close
leaned Wyoming +1.5Cover ✓
margin err: model 4.6 · mkt 8.5 · closer
Model
pred Utah State 0.5 · actual Hawai'i 18
winner Utah State
ATS vs close
leaned Hawai'i +1.5Cover ✓
margin err: model 18.5 · mkt 19.5 · closer
Model
pred Fresno State 1.7 · actual Colorado State 28
winner Fresno State
ATS vs close
leaned Colorado State +5.5Cover ✓
margin err: model 29.7 · mkt 33.5 · closer
Model
pred San Diego State 9.4 · actual San Diego State 34
winner San Diego State
ATS vs close
leaned San Diego State -6.5Cover ✓
margin err: model 24.6 · mkt 27.5 · 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.