CFB Betting Edge

2024 · Week 6 · ACC · backtest — what the model predicted vs what happened, and vs the market
Week 6 backtest · ACC · 9 games — what the model predicted vs what happened
Straight up
5–456%
ATS vs close
3–5 · 1P38%
Model margin MAE
9.6
Market margin MAE
7.7
→ 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 @ UNLVFinal 4441
Model
pred UNLV 9.8 · actual Syracuse 3
winner UNLV
ATS vs close
leaned UNLV -5.5Miss ✗
margin err: model 12.8 · mkt 8.5 · mkt closer
Model
pred NC State 6.0 · actual Wake Forest 4
winner NC State
ATS vs close
leaned NC State -4.0Miss ✗
margin err: model 10.0 · mkt 8.0 · mkt closer
Model
pred North Carolina 4.1 · actual Pittsburgh 10
winner North Carolina
ATS vs close
leaned North Carolina +2.5Miss ✗
margin err: model 14.1 · mkt 7.5 · mkt closer
Duke @ Georgia TechFinal 1424
Model
pred Georgia Tech 2.2 · actual Georgia Tech 10
winner Georgia Tech
ATS vs close
leaned Duke +10.0Push
margin err: model 7.8 · mkt 0.0 · mkt closer
SMU @ LouisvilleFinal 3427
Model
pred Louisville 1.3 · actual SMU 7
winner Louisville
ATS vs close
leaned SMU +6.5Cover ✓
margin err: model 8.3 · mkt 13.5 · closer
Model
pred Virginia 0.3 · actual Virginia 10
winner Virginia
ATS vs close
leaned Boston College +2.0Miss ✗
margin err: model 9.7 · mkt 8.0 · mkt closer
Miami @ CaliforniaFinal 3938
Model
pred Miami 10.1 · actual Miami 1
winner Miami
ATS vs close
leaned Miami -10.0Miss ✗
margin err: model 9.1 · mkt 9.0 · mkt closer
Model
pred Clemson 11.8 · actual Clemson 16
winner Clemson
ATS vs close
leaned Florida State +16.5Cover ✓
margin err: model 4.2 · mkt 0.5 · mkt closer
Model
pred Virginia Tech 13.7 · actual Virginia Tech 24
winner Virginia Tech
ATS vs close
leaned Virginia Tech -9.5Cover ✓
margin err: model 10.3 · mkt 14.5 · 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.