CFB
›

CFB Betting Edge

2025 · Week 14 · Sun Belt · 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 14 backtest · Sun Belt · 7 games — what the model predicted vs what happened
Straight up
4–357%
ATS vs close
5–271%
Model margin MAE
13.1
Market margin MAE
13.0
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Georgia State @ Old DominionFinal 10–27
Model
pred Old Dominion 18.0 · actual Old Dominion 17
winner Old Dominion ✓
ATS vs close
leaned Georgia State +28.5Cover ✓
margin err: model 1.0 · mkt 11.5 · closer
UL Monroe @ LouisianaFinal 27–30
Model
pred Louisiana 12.9 · actual Louisiana 3
winner Louisiana ✓
ATS vs close
leaned Louisiana -11.0Miss ✗
margin err: model 9.9 · mkt 8.0 · mkt closer
South Alabama @ Texas StateFinal 26–49
Model
pred Texas State 12.4 · actual Texas State 23
winner Texas State ✓
ATS vs close
leaned Texas State -9.5Cover ✓
margin err: model 10.6 · mkt 13.5 · closer
Georgia Southern @ MarshallFinal 24–19
Model
pred Marshall 9.1 · actual Georgia Southern 5
winner Marshall ✗
ATS vs close
leaned Georgia Southern +10.5Cover ✓
margin err: model 14.1 · mkt 15.5 · closer
Arkansas State @ App StateFinal 30–29
Model
pred App State 2.7 · actual Arkansas State 1
winner App State ✗
ATS vs close
leaned App State +1.5Cover ✓
margin err: model 3.7 · mkt 0.5 · mkt closer
Troy @ Southern MissFinal 28–18
Model
pred Southern Miss 0.6 · actual Troy 10
winner Southern Miss ✗
ATS vs close
leaned Troy +7.0Cover ✓
margin err: model 10.6 · mkt 17.0 · closer
James Madison @ Coastal CarolinaFinal 59–10
Model
pred James Madison 7.0 · actual James Madison 49
winner James Madison ✓
ATS vs close
leaned Coastal Carolina +24.0Miss ✗
margin err: model 42.0 · mkt 25.0 · 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.