The pickThe locked winner and its win probability. A priced game's number is built on the market's no-vig price; the model's own margin and total sit beside the market's below, as context.
locked before kickoff
Win chance
55%Virginia CavaliersLean✗
Built on the market's no-vig price. Model alone: Duke Blue Devils 52%, the other way, so the margin and score here are the model's own read and lean opposite the pick.
Model marginThe model's own predicted margin beside the market's number. Context for reading the game: the model makes no spread pick.
DUKE by 0.8market UVA by 2.5
Model totalThe model's own predicted total points beside the market's number. Context for reading the game: the model makes no over/under pick.
48.7 pointsmarket 47.5
Why the model calls itThe reasons behind the winner call, in plain sentences drawn from this page's numbers.
The model has Virginia Cavaliers at 55% to win, with the market at UVA by 2.5.
Counterpoint: sack rate favours DUKE. DUKE sack rate ranks #2, UVA defends it at #52; the other way UVA #134 into DUKE's #36. The pick still lands on UVA because it rests on the whole season's results and the market's price, not one area.
Form: DUKE has the better last five games by 16.2 points a game (UVA -0.4, DUKE +15.8).
Home field is with UVA, which supports the pick.
ContextThe model makes it DUKE by 0.8 against a market UVA by 2.5: 3.3 points of daylight in DUKE's favour. The model's total is 48.7 against a line of 47.5: in line with the market.The model makes no spread or over/under pick: neither has shown an edge over the market in our backtests.
Matchup context: who has the advantageWhich team has the advantage in each area, and how clearly. Context for reading the game, not model inputs.
Model DUKE by 0.8 · market UVA by 2.5
ⓘContext, not inputs. These areas show how the two sides match up so you can read the game. The model's call comes from the teams' overall ratings, the quarterback, rest, home field and weather, not from these tiles.
Passing game
DUKE
Slight advantage
DUKE passing ranks #42, UVA defends it at #77; the other way UVA #69 into DUKE's #75.
Rushing game
DUKE
Slight advantage
DUKE rushing ranks #55, UVA defends it at #84; the other way UVA #30 into DUKE's #17.
Third down & red zone
DUKE
Clear advantage
DUKE third-down conversion ranks #41, UVA defends it at #29; the other way UVA #123 into DUKE's #9.
Big plays
DUKE
Clear advantage
DUKE pass explosiveness ranks #65, UVA defends it at #90; the other way UVA #131 into DUKE's #22.
Pass protection & rush
DUKE
Clear advantage
DUKE sack rate ranks #2, UVA defends it at #52; the other way UVA #134 into DUKE's #36.
Ball security
=
Even
DUKE turnovers / game ranks #10, UVA defends it at #87; the other way UVA #19 into DUKE's #95.
Form (last 5)
DUKE
Clear advantage
UVA −0.4 per game over the last five, DUKE +15.8.
Market
UVA
Slight advantage
Consensus has UVA by 2.5; the model says DUKE by 0.8.
the market, for comparison
Where the lines sitWhere the market's number and the model's sit among every final margin and total in the league's history; the highlighted bars are the games that landed between the two.
3,330 FBS games since 2023
Marginmarket UVA by 2.5 · model DUKE by 0.8
Mkt UVA 2.5
Model DUKE 0.8
← DUKE by 28tieUVA by 28 →
2.8% of FBS games land between the two numbers. Most common margins: 3 (9.7%), 7 (7.6%), 10 (4.3%), 14 (4.1%).
Totalmarket 47.5 · model 48.7
Mkt 47.5
Model 48.7
24 pts6096 pts
3.3% of FBS games finish between 47.5 and 48.7. The league’s median total since 2023 is 52.
Sharp read
tap to open+
Where the market maker moved the line since open, and whether other books followed. Tracked, not a pick.
Spread
Sharp side: UVAModel disagrees
Opened
UVA -2.5
→
Market maker now
UVA -2.25
▲ 0.5 since open
→
Retail now
UVA -2.5
in line
37 moves8 books7 led
Sun, Oct 18, 7:49 PM first sharp move: UVA -2 → UVA -1
1 book followed within six hours
Retail was still UVA -2.5 at that point
Total
Sharp side: the overModel agrees
Opened
47.5
→
Market maker now
47.3
▲ 0.5 since open
→
Retail now
47.5
in line
35 moves8 books2 led
Wed, Oct 21, 10:11 PM first sharp move: 46.5 → 47
No books followed within six hours
Retail was still 47.5 at that point
The model alone was backtested walk-forward (each game priced only from what came before it). Since the winner call started following the market, the calibration that counts is the record of locked picks on the results page. Margin and total are context, not picks. Model reads, not personalized advice. For information only, not betting advice. 21+ only. Gambling problem? Call or text 1-800-GAMBLER.
