CFB Betting Edge

2024 · Week 11 · ACC · backtest — what the model predicted vs what happened, and vs the market
Week 11 backtest · ACC · 7 games — what the model predicted vs what happened
Straight up
5–271%
ATS vs close
5–271%
Model margin MAE
9.5
Market margin MAE
10.6
→ model's margins were closer than the market
Results — model read vs the final score + how the closing-line lean held up
Model
pred Notre Dame 17.3 · actual Notre Dame 49
winner Notre Dame
ATS vs close
leaned Florida State +25.5Miss ✗
margin err: model 31.7 · mkt 23.5 · mkt closer
Model
pred Boston College 5.6 · actual Boston College 6
winner Boston College
ATS vs close
leaned Boston College -3.0Cover ✓
margin err: model 0.4 · mkt 3.0 · closer
Model
pred Pittsburgh 2.4 · actual Virginia 5
winner Pittsburgh
ATS vs close
leaned Virginia +7.5Cover ✓
margin err: model 7.4 · mkt 12.5 · closer
Duke @ NC StateFinal 2919
Model
pred Duke 1.5 · actual Duke 10
winner Duke
ATS vs close
leaned Duke +3.0Cover ✓
margin err: model 8.5 · mkt 13.0 · closer
Model
pred Clemson 2.4 · actual Clemson 10
winner Clemson
ATS vs close
leaned Virginia Tech +5.5Miss ✗
margin err: model 7.6 · mkt 4.5 · mkt closer
Model
pred Miami 5.8 · actual Georgia Tech 5
winner Miami
ATS vs close
leaned Georgia Tech +9.5Cover ✓
margin err: model 10.8 · mkt 14.5 · closer
Model
pred California 9.6 · actual California 10
winner California
ATS vs close
leaned California -7.0Cover ✓
margin err: model 0.4 · mkt 3.0 · 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.