CFB Betting Edge
2025 · Week 10 · ACC · backtest — what the model predicted vs what happened, and vs the market
AllSECBig TenBig 12ACCPac-12American AthleticMountain WestSun BeltMid-AmericanConference USAFBS Independents
Week 10 backtest · ACC · 9 games — what the model predicted vs what happened
Straight up
6–367%
ATS vs close
3–633%
Model margin MAE
12.2
Market margin MAE
11.1
Results — model read vs the final score + how the closing-line lean held up
Duke @ ClemsonFinal 46–45
Model
pred Clemson 11.7 · actual Duke 1
winner Clemson ✗
ATS vs close
leaned Clemson -4.0Miss ✗
margin err: model 12.7 · mkt 5.0 · mkt closer
Wake Forest @ Florida StateFinal 7–42
Model
pred Florida State 6.0 · actual Florida State 35
winner Florida State ✓
ATS vs close
leaned Wake Forest +12.5Miss ✗
margin err: model 29.0 · mkt 22.5 · mkt closer
North Carolina @ SyracuseFinal 27–10
Model
pred Syracuse 2.6 · actual North Carolina 17
winner Syracuse ✗
ATS vs close
leaned Syracuse -1.5Miss ✗
margin err: model 19.6 · mkt 18.5 · mkt closer
Miami @ SMUFinal 20–26
Model
pred SMU 2.0 · actual SMU 6
winner SMU ✓
ATS vs close
leaned SMU +8.5Cover ✓
margin err: model 4.0 · mkt 14.5 · closer
Virginia @ CaliforniaFinal 31–21
Model
pred Virginia 0.1 · actual Virginia 10
winner Virginia ✓
ATS vs close
leaned California +6.5Miss ✗
margin err: model 9.9 · mkt 3.5 · mkt closer
Georgia Tech @ NC StateFinal 36–48
Model
pred Georgia Tech 6.5 · actual NC State 12
winner Georgia Tech ✗
ATS vs close
leaned Georgia Tech -4.5Miss ✗
margin err: model 18.5 · mkt 16.5 · mkt closer
Louisville @ Virginia TechFinal 28–16
Model
pred Louisville 10.6 · actual Louisville 12
winner Louisville ✓
ATS vs close
leaned Louisville -10.5Cover ✓
margin err: model 1.4 · mkt 1.5 · closer
Pittsburgh @ StanfordFinal 35–20
Model
pred Pittsburgh 13.4 · actual Pittsburgh 15
winner Pittsburgh ✓
ATS vs close
leaned Stanford +13.5Miss ✗
margin err: model 1.6 · mkt 1.5 · mkt closer
Notre Dame @ Boston CollegeFinal 25–10
Model
pred Notre Dame 28.5 · actual Notre Dame 15
winner Notre Dame ✓
ATS vs close
leaned Boston College +31.0Cover ✓
margin err: model 13.5 · mkt 16.0 · 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.