CFB Betting Edge
2025 · 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
1–517%
Model margin MAE
10.5
Market margin MAE
10.8
Results — model read vs the final score + how the closing-line lean held up
NC State @ Notre DameFinal 7–36
Model
pred Notre Dame 19.2 · actual Notre Dame 29
winner Notre Dame ✓
ATS vs close
leaned NC State +23.5Miss ✗
margin err: model 9.8 · mkt 5.5 · mkt closer
Stanford @ SMUFinal 10–34
Model
pred SMU 19.1 · actual SMU 24
winner SMU ✓
ATS vs close
leaned Stanford +19.5Miss ✗
margin err: model 4.9 · mkt 4.5 · mkt closer
Virginia Tech @ Georgia TechFinal 20–35
Model
pred Georgia Tech 13.9 · actual Georgia Tech 15
winner Georgia Tech ✓
ATS vs close
leaned Virginia Tech +14.0Miss ✗
margin err: model 1.1 · mkt 1.0 · mkt closer
Pittsburgh @ Florida StateFinal 34–31
Model
pred Florida State 1.9 · actual Pittsburgh 3
winner Florida State ✗
ATS vs close
leaned Pittsburgh +10.5Cover ✓
margin err: model 4.9 · mkt 13.5 · closer
Wake Forest @ Oregon StateFinal 39–14
Model
pred Wake Forest 0.3 · actual Wake Forest 25
winner Wake Forest ✓
ATS vs close
leaned Oregon State +1.5Miss ✗
margin err: model 24.7 · mkt 23.5 · mkt closer
Clemson @ Boston CollegeFinal 41–10
Model
pred Clemson 13.1 · actual Clemson 31
winner Clemson ✓
ATS vs close
leaned Boston College +14.0Miss ✗
margin err: model 17.9 · mkt 17.0 · mkt 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.