CFB Betting Edge

2025 · Week 1 · Sun Belt · backtest — what the model predicted vs what happened, and vs the market
Week 1 backtest · Sun Belt · 9 games — what the model predicted vs what happened
Straight up
7–278%
ATS vs close
5–456%
Model margin MAE
17.9
Market margin MAE
14.1
→ 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 Ole Miss 25.2 · actual Ole Miss 56
winner Ole Miss
ATS vs close
leaned Georgia State +33.5Miss ✗
margin err: model 30.8 · mkt 22.5 · mkt closer
Model
pred Indiana 20.7 · actual Indiana 13
winner Indiana
ATS vs close
leaned Old Dominion +23.5Cover ✓
margin err: model 7.7 · mkt 10.5 · closer
Marshall @ GeorgiaFinal 745
Model
pred Georgia 18.6 · actual Georgia 38
winner Georgia
ATS vs close
leaned Marshall +38.5Cover ✓
margin err: model 19.4 · mkt 0.5 · mkt closer
Model
pred Texas State 17.8 · actual Texas State 25
winner Texas State
ATS vs close
leaned Texas State -14.0Cover ✓
margin err: model 7.2 · mkt 11.0 · closer
Model
pred Virginia 2.6 · actual Virginia 41
winner Virginia
ATS vs close
leaned Coastal Carolina +13.5Miss ✗
margin err: model 38.4 · mkt 27.5 · mkt closer
Rice @ LouisianaFinal 1412
Model
pred Louisiana 1.7 · actual Rice 2
winner Louisiana
ATS vs close
leaned Rice +9.5Cover ✓
margin err: model 3.7 · mkt 11.5 · closer
Model
pred App State 3.5 · actual App State 23
winner App State
ATS vs close
leaned Charlotte +8.5Miss ✗
margin err: model 19.5 · mkt 14.5 · mkt closer
Model
pred Georgia Southern 4.7 · actual Fresno State 28
winner Georgia Southern
ATS vs close
leaned Georgia Southern +2.0Miss ✗
margin err: model 32.7 · mkt 26.0 · mkt closer
Model
pred Mississippi State 18.5 · actual Mississippi State 17
winner Mississippi State
ATS vs close
leaned Mississippi State -14.5Cover ✓
margin err: model 1.5 · mkt 2.5 · 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.