CFB Betting Edge

2025 · Week 14 · Mountain West · backtest — what the model predicted vs what happened, and vs the market
Week 14 backtest · Mountain West · 6 games — what the model predicted vs what happened
Straight up
3–350%
ATS vs close
0–50%
Model margin MAE
16.7
Market margin MAE
13.2
→ 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 Colorado State 6.9 · actual Air Force 21
winner Colorado State
ATS vs close
leaned Colorado State +2.5Miss ✗
margin err: model 27.9 · mkt 18.5 · mkt closer
Wyoming @ Hawai'iFinal 727
Model
pred Hawai'i 6.8 · actual Hawai'i 20
winner Hawai'i
ATS vs close
leaned Wyoming +8.5Miss ✗
margin err: model 13.2 · mkt 11.5 · mkt closer
Model
pred San José State 0.5 · actual Fresno State 27
winner San José State
ATS vs close
leaned San José State +3.5Miss ✗
margin err: model 27.5 · mkt 23.5 · mkt closer
Model
pred San Diego State 2.2 · actual New Mexico 6
winner San Diego State
ATS vs close
leaned San Diego State -1.5Miss ✗
margin err: model 8.2 · mkt 7.5 · mkt closer
Model
pred Boise State 6.8 · actual Boise State 1
winner Boise State
ATS vs close
leaned Boise State -1.5Miss ✗
margin err: model 5.8 · mkt 0.5 · mkt closer
UNLV @ NevadaFinal 4217
Model
pred UNLV 7.5 · actual UNLV 25
winner UNLV
ATS vs close
model matched the close — no lean
margin err: model 17.5 · mkt 17.5 · tie
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.