CFB Betting Edge

2024 · Week 5 · ACC · backtest — what the model predicted vs what happened, and vs the market
Week 5 backtest · ACC · 8 games — what the model predicted vs what happened
Straight up
8–0100%
ATS vs close
5–2 · 1P71%
Model margin MAE
7.0
Market margin MAE
6.4
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Stanford @ ClemsonFinal 1440
Model
pred Clemson 20.1 · actual Clemson 26
winner Clemson
ATS vs close
leaned Stanford +24.0Miss ✗
margin err: model 5.9 · mkt 2.0 · mkt closer
Model
pred Miami 14.7 · actual Miami 4
winner Miami
ATS vs close
leaned Virginia Tech +17.5Cover ✓
margin err: model 10.7 · mkt 13.5 · closer
Model
pred Boston College 13.6 · actual Boston College 1
winner Boston College
ATS vs close
leaned Boston College -7.5Miss ✗
margin err: model 12.6 · mkt 6.5 · mkt closer
Florida State @ SMUFinal 1642
Model
pred SMU 12.9 · actual SMU 26
winner SMU
ATS vs close
leaned SMU -6.0Cover ✓
margin err: model 13.1 · mkt 20.0 · closer
Model
pred Notre Dame 7.6 · actual Notre Dame 7
winner Notre Dame
ATS vs close
leaned Notre Dame -6.5Cover ✓
margin err: model 0.6 · mkt 0.5 · mkt closer
Model
pred Duke 4.6 · actual Duke 1
winner Duke
ATS vs close
leaned Duke +1.5Cover ✓
margin err: model 3.6 · mkt 2.5 · mkt closer
Model
pred NC State 1.9 · actual NC State 7
winner NC State
ATS vs close
leaned Northern Illinois +7.0Push
margin err: model 5.1 · mkt 0.0 · mkt closer
Model
pred Louisiana 7.3 · actual Louisiana 3
winner Louisiana
ATS vs close
leaned Louisiana +3.0Cover ✓
margin err: model 4.3 · mkt 6.0 · 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.