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.
backtest · not locked
Win chance
56%Duke Blue DevilsLean
No moneyline was priced into this call, so it is the model's own number.
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 2.5market DUKE by 7
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.
52.6 pointsmarket 50.5
Backtest, not locked: this game finished before the model ran on it; the calls were reconstructed from pre-game information.
Why the model calls itThe reasons behind the winner call, in plain sentences drawn from this page's numbers.
The model has Duke Blue Devils at 56% to win, with the market at DUKE by 7.
DUKE has the advantage in rushing: DUKE rushing ranks #76, UNC defends it at #98; the other way UNC #123 into DUKE's #55.
Form: DUKE has the better last five games by 8.2 points a game (UNC -4.8, DUKE +3.4).
Home field is with UNC, which the pick has to overcome.
ContextThe model makes it DUKE by 2.5 against a market DUKE by 7: 4.5 points of daylight in UNC's favour. The model's total is 52.6 against a line of 50.5: 2.1 points above it.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 2.5 · market DUKE by 7
ⓘ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
=
Even
UNC passing ranks #68, DUKE defends it at #119; the other way DUKE #26 into UNC's #65.
Rushing game
DUKE
Clear advantage
DUKE rushing ranks #76, UNC defends it at #98; the other way UNC #123 into DUKE's #55.
Third down & red zone
=
Even
DUKE points / scoring opportunity ranks #26, UNC defends it at #61; the other way UNC #107 into DUKE's #128.
Big plays
=
Even
DUKE rush explosiveness ranks #64, UNC defends it at #92; the other way UNC #131 into DUKE's #89.
Pass protection & rush
UNC
Slight advantage
UNC sack rate ranks #66, DUKE defends it at #95; the other way DUKE #37 into UNC's #31.
Ball security
DUKE
Clear advantage
DUKE turnovers / game ranks #29, UNC defends it at #100; the other way UNC #69 into DUKE's #23.
Form (last 5)
DUKE
Clear advantage
UNC −4.8 per game over the last five, DUKE +3.4.
Market
DUKE
Clear advantage
Consensus has DUKE by 7; the model says DUKE by 2.5.
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.
3,154 FBS games since 2023
Marginmarket DUKE by 7 · model DUKE by 2.5
Mkt DUKE 7
Model DUKE 2.5
← DUKE by 28tieUNC by 28 →
8.0% of FBS games land between the two numbers. The market is on 7, a number 7.5% of games land on exactly (a push). The model’s number is across the key number 3. Most common margins: 3 (9.3%), 7 (7.5%), 10 (4.3%), 14 (4.1%).
Totalmarket 50.5 · model 52.6
Mkt 50.5
Model 52.6
24 pts6096 pts
6.0% of FBS games finish between 50.5 and 52.6. The league’s median total since 2023 is 53.
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.
