CFB Betting Edge

2024 · Week 4 · ACC · backtest — what the model predicted vs what happened, and vs the market
Week 4 backtest · ACC · 11 games — what the model predicted vs what happened
Straight up
6–555%
ATS vs close
7–464%
Model margin MAE
12.1
Market margin MAE
12.2
→ model's margins were closer than the market
Results — model read vs the final score + how the closing-line lean held up
Model
pred Louisville 20.4 · actual Louisville 12
winner Louisville
ATS vs close
leaned Louisville -8.5Cover ✓
margin err: model 8.4 · mkt 3.5 · mkt closer
NC State @ ClemsonFinal 3559
Model
pred Clemson 19.6 · actual Clemson 24
winner Clemson
ATS vs close
leaned Clemson -17.5Cover ✓
margin err: model 4.4 · mkt 6.5 · closer
Model
pred North Carolina 14.6 · actual James Madison 20
winner North Carolina
ATS vs close
leaned North Carolina -11.0Miss ✗
margin err: model 34.6 · mkt 31.0 · mkt closer
Model
pred Coastal Carolina 12.5 · actual Virginia 19
winner Coastal Carolina
ATS vs close
leaned Coastal Carolina +3.5Miss ✗
margin err: model 31.5 · mkt 15.5 · mkt closer
Model
pred Boston College 6.9 · actual Boston College 4
winner Boston College
ATS vs close
leaned Boston College -4.5Miss ✗
margin err: model 2.9 · mkt 0.5 · mkt closer
TCU @ SMUFinal 4266
Model
pred SMU 6.5 · actual SMU 24
winner SMU
ATS vs close
leaned SMU +1.5Cover ✓
margin err: model 17.5 · mkt 25.5 · closer
Stanford @ SyracuseFinal 2624
Model
pred Syracuse 5.4 · actual Stanford 2
winner Syracuse
ATS vs close
leaned Stanford +9.5Cover ✓
margin err: model 7.4 · mkt 11.5 · closer
Model
pred Virginia Tech 0.1 · actual Rutgers 3
winner Virginia Tech
ATS vs close
leaned Rutgers +3.3Cover ✓
margin err: model 3.1 · mkt 6.3 · closer
Model
pred California 4.4 · actual Florida State 5
winner California
ATS vs close
leaned California +3.0Miss ✗
margin err: model 9.4 · mkt 2.0 · mkt closer
Model
pred Miami 24.2 · actual Miami 35
winner Miami
ATS vs close
leaned Miami -16.5Cover ✓
margin err: model 10.8 · mkt 18.5 · closer
Model
pred Duke 24.5 · actual Duke 28
winner Duke
ATS vs close
leaned Duke -14.5Cover ✓
margin err: model 3.5 · mkt 13.5 · 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.