CFB
›

CFB Betting Edge

2025 · Week 5 · ACC · backtest — what the model predicted vs what happened, and vs the market
AllSECBig TenBig 12ACCPac-12American AthleticMountain WestSun BeltMid-AmericanConference USAFBS Independents
Season202620252024
Week123456789101112131415
Week 5 backtest · ACC · 7 games — what the model predicted vs what happened
Straight up
3–443%
ATS vs close
3–350%
Model margin MAE
13.4
Market margin MAE
12.3
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Virginia Tech @ NC StateFinal 23–21
Model
pred NC State 14.4 · actual Virginia Tech 2
winner NC State ✗
ATS vs close
leaned NC State -10.0Miss ✗
margin err: model 16.4 · mkt 12.0 · mkt closer
California @ Boston CollegeFinal 28–24
Model
pred Boston College 6.0 · actual California 4
winner Boston College ✗
ATS vs close
model matched the close — no lean
margin err: model 10.0 · mkt 10.0 · tie
San José State @ StanfordFinal 29–30
Model
pred Stanford 5.2 · actual Stanford 1
winner Stanford ✓
ATS vs close
leaned Stanford -3.0Miss ✗
margin err: model 4.2 · mkt 2.0 · mkt closer
Duke @ SyracuseFinal 38–3
Model
pred Syracuse 3.9 · actual Duke 35
winner Syracuse ✗
ATS vs close
leaned Syracuse +4.0Miss ✗
margin err: model 38.9 · mkt 31.0 · mkt closer
Florida State @ VirginiaFinal 38–46
Model
pred Florida State 4.2 · actual Virginia 8
winner Florida State ✗
ATS vs close
leaned Virginia +7.0Cover ✓
margin err: model 12.2 · mkt 15.0 · closer
Louisville @ PittsburghFinal 34–27
Model
pred Louisville 5.2 · actual Louisville 7
winner Louisville ✓
ATS vs close
leaned Louisville -3.0Cover ✓
margin err: model 1.8 · mkt 4.0 · closer
Georgia Tech @ Wake ForestFinal 30–29
Model
pred Georgia Tech 11.4 · actual Georgia Tech 1
winner Georgia Tech ✓
ATS vs close
leaned Wake Forest +13.0Cover ✓
margin err: model 10.4 · mkt 12.0 · 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.