CFB Betting Edge
2024 · Week 7 · ACC · backtest — what the model predicted vs what happened, and vs the market
AllSECBig TenBig 12ACCPac-12American AthleticMountain WestSun BeltMid-AmericanConference USAFBS Independents
Week 7 backtest · ACC · 6 games — what the model predicted vs what happened
Straight up
5–183%
ATS vs close
4–267%
Model margin MAE
7.8
Market margin MAE
7.9
Results — model read vs the final score + how the closing-line lean held up
Stanford @ Notre DameFinal 7–49
Model
pred Notre Dame 26.7 · actual Notre Dame 42
winner Notre Dame ✓
ATS vs close
leaned Notre Dame -22.5Cover ✓
margin err: model 15.3 · mkt 19.5 · closer
California @ PittsburghFinal 15–17
Model
pred Pittsburgh 4.6 · actual Pittsburgh 2
winner Pittsburgh ✓
ATS vs close
leaned Pittsburgh -3.5Miss ✗
margin err: model 2.6 · mkt 1.5 · mkt closer
Georgia Tech @ North CarolinaFinal 41–34
Model
pred North Carolina 1.0 · actual Georgia Tech 7
winner North Carolina ✗
ATS vs close
leaned North Carolina +3.5Miss ✗
margin err: model 8.0 · mkt 3.5 · mkt closer
Louisville @ VirginiaFinal 24–20
Model
pred Louisville 0.6 · actual Louisville 4
winner Louisville ✓
ATS vs close
leaned Virginia +7.0Cover ✓
margin err: model 3.4 · mkt 3.0 · mkt closer
Syracuse @ NC StateFinal 24–17
Model
pred Syracuse 1.7 · actual Syracuse 7
winner Syracuse ✓
ATS vs close
leaned Syracuse -1.0Cover ✓
margin err: model 5.3 · mkt 6.0 · closer
Clemson @ Wake ForestFinal 49–14
Model
pred Clemson 23.0 · actual Clemson 35
winner Clemson ✓
ATS vs close
leaned Clemson -21.0Cover ✓
margin err: model 12.0 · mkt 14.0 · 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.