CFB Betting Edge
2025 · Week 9 · 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 9 backtest · Conference USA · 4 games — what the model predicted vs what happened
Straight up
1–325%
ATS vs close
0–40%
Model margin MAE
16.7
Market margin MAE
8.0
Results — model read vs the final score + how the closing-line lean held up
Middle Tennessee @ DelawareFinal 28–31
Model
pred Delaware 17.3 · actual Delaware 3
winner Delaware ✓
ATS vs close
leaned Delaware -8.5Miss ✗
margin err: model 14.3 · mkt 5.5 · mkt closer
Missouri State @ New Mexico StateFinal 24–17
Model
pred New Mexico State 15.9 · actual Missouri State 7
winner New Mexico State ✗
ATS vs close
leaned New Mexico State +2.5Miss ✗
margin err: model 22.9 · mkt 4.5 · mkt closer
Western Kentucky @ Louisiana TechFinal 28–27
Model
pred Louisiana Tech 8.1 · actual Western Kentucky 1
winner Louisiana Tech ✗
ATS vs close
leaned Louisiana Tech -5.0Miss ✗
margin err: model 9.1 · mkt 6.0 · mkt closer
Kennesaw State @ Florida InternationalFinal 45–26
Model
pred Florida International 1.6 · actual Kennesaw State 19
winner Florida International ✗
ATS vs close
leaned Florida International +3.0Miss ✗
margin err: model 20.6 · mkt 16.0 · 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.