CFB Betting Edge

2025 · Week 6 · ACC · backtest — what the model predicted vs what happened, and vs the market
Week 6 backtest · ACC · 7 games — what the model predicted vs what happened
Straight up
3–443%
ATS vs close
3–443%
Model margin MAE
14.3
Market margin MAE
13.6
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Syracuse @ SMUFinal 1831
Model
pred SMU 14.4 · actual SMU 13
winner SMU
ATS vs close
leaned Syracuse +17.5Cover ✓
margin err: model 1.4 · mkt 4.5 · closer
Model
pred Louisville 6.9 · actual Virginia 3
winner Louisville
ATS vs close
leaned Louisville -6.5Miss ✗
margin err: model 9.9 · mkt 9.5 · mkt closer
Model
pred Pittsburgh 5.8 · actual Pittsburgh 41
winner Pittsburgh
ATS vs close
leaned Boston College +6.5Miss ✗
margin err: model 35.2 · mkt 34.5 · mkt closer
Model
pred Florida State 4.0 · actual Miami 6
winner Florida State
ATS vs close
leaned Florida State +3.5Miss ✗
margin err: model 10.0 · mkt 2.5 · mkt closer
Duke @ CaliforniaFinal 4521
Model
pred California 0.5 · actual Duke 24
winner California
ATS vs close
leaned California +3.5Miss ✗
margin err: model 24.5 · mkt 20.5 · mkt closer
Model
pred Virginia Tech 0.1 · actual Wake Forest 7
winner Virginia Tech
ATS vs close
leaned Wake Forest +4.5Cover ✓
margin err: model 7.1 · mkt 11.5 · closer
Model
pred Clemson 16.2 · actual Clemson 28
winner Clemson
ATS vs close
leaned Clemson -15.5Cover ✓
margin err: model 11.8 · mkt 12.5 · 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.