CFB
›

CFB Betting Edge

2025 · Week 12 · Conference USA · backtest — what the model predicted vs what happened, and vs the market
AllSECBig TenBig 12ACCPac-12American AthleticMountain WestSun BeltMid-AmericanConference USAFBS Independents
Season202620252024
Week123456789101112131415
Week 12 backtest · Conference USA · 7 games — what the model predicted vs what happened
Straight up
4–357%
ATS vs close
4–357%
Model margin MAE
9.3
Market margin MAE
10.0
→ model's margins were closer than the market
Results — model read vs the final score + how the closing-line lean held up
New Mexico State @ TennesseeFinal 9–42
Model
pred Tennessee 31.3 · actual Tennessee 33
winner Tennessee ✓
ATS vs close
leaned New Mexico State +41.5Cover ✓
margin err: model 1.7 · mkt 8.5 · closer
Kennesaw State @ Jacksonville StateFinal 26–35
Model
pred Jacksonville State 9.8 · actual Jacksonville State 9
winner Jacksonville State ✓
ATS vs close
leaned Jacksonville State +3.5Cover ✓
margin err: model 0.8 · mkt 12.5 · closer
UTEP @ Missouri StateFinal 24–38
Model
pred Missouri State 9.7 · actual Missouri State 14
winner Missouri State ✓
ATS vs close
leaned Missouri State -6.5Cover ✓
margin err: model 4.3 · mkt 7.5 · closer
Middle Tennessee @ Western KentuckyFinal 26–42
Model
pred Western Kentucky 9.5 · actual Western Kentucky 16
winner Western Kentucky ✓
ATS vs close
leaned Middle Tennessee +13.5Miss ✗
margin err: model 6.5 · mkt 2.5 · mkt closer
Louisiana Tech @ Washington StateFinal 3–28
Model
pred Louisiana Tech 2.2 · actual Washington State 25
winner Louisiana Tech ✗
ATS vs close
leaned Louisiana Tech +10.0Miss ✗
margin err: model 27.2 · mkt 15.0 · mkt closer
Delaware @ Sam HoustonFinal 23–26
Model
pred Delaware 3.1 · actual Sam Houston 3
winner Delaware ✗
ATS vs close
leaned Sam Houston +11.5Cover ✓
margin err: model 6.1 · mkt 14.5 · closer
Liberty @ Florida InternationalFinal 27–34
Model
pred Liberty 11.2 · actual Florida International 7
winner Liberty ✗
ATS vs close
leaned Liberty -2.5Miss ✗
margin err: model 18.2 · mkt 9.5 · 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.