CFB Betting Edge
2025 · Week 1 · Conference USA · backtest — what the model predicted vs what happened, and vs the market
AllSECBig TenBig 12ACCPac-12American AthleticMountain WestSun BeltMid-AmericanConference USAFBS Independents
Week 1 backtest · Conference USA · 6 games — what the model predicted vs what happened
Straight up
5–183%
ATS vs close
3–350%
Model margin MAE
14.8
Market margin MAE
12.9
Results — model read vs the final score + how the closing-line lean held up
Missouri State @ USCFinal 13–73
Model
pred USC 23.2 · actual USC 60
winner USC ✓
ATS vs close
leaned Missouri State +36.5Miss ✗
margin err: model 36.8 · mkt 23.5 · mkt closer
Kennesaw State @ Wake ForestFinal 9–10
Model
pred Wake Forest 18.8 · actual Wake Forest 1
winner Wake Forest ✓
ATS vs close
leaned Wake Forest -18.5Miss ✗
margin err: model 17.8 · mkt 17.5 · mkt closer
UTEP @ Utah StateFinal 16–28
Model
pred Utah State 5.9 · actual Utah State 12
winner Utah State ✓
ATS vs close
leaned Utah State -4.5Cover ✓
margin err: model 6.1 · mkt 7.5 · closer
Jacksonville State @ UCFFinal 10–17
Model
pred UCF 5.1 · actual UCF 7
winner UCF ✓
ATS vs close
leaned Jacksonville State +20.5Cover ✓
margin err: model 1.9 · mkt 13.5 · closer
Sam Houston @ Western KentuckyFinal 24–41
Model
pred Sam Houston 1.8 · actual Western Kentucky 17
winner Sam Houston ✗
ATS vs close
leaned Sam Houston +9.5Miss ✗
margin err: model 18.8 · mkt 7.5 · mkt closer
UNLV @ Sam HoustonFinal 38–21
Model
pred UNLV 9.7 · actual UNLV 17
winner UNLV ✓
ATS vs close
leaned UNLV -9.0Cover ✓
margin err: model 7.3 · mkt 8.0 · 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.