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
59%Dallas CowboysLean
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.
DAL by 3.2market DAL by 3.5
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.
63.2 pointsmarket 52.5
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 Dallas Cowboys at 59% to win, with the market at DAL by 3.5.
Quarterback: the pick was locked with Jalen Hurts starting for Philadelphia Eagles, and the model prices that in.
DAL has the advantage in passing: DAL passing ranks #3, PHI defends it at #28; the other way PHI #11 into DAL's #8.
DAL has the advantage in rushing: DAL rushing ranks #10, PHI defends it at #30; the other way PHI #8 into DAL's #12.
Rest: DAL has 3 more days since its last game (DAL 10d, PHI 7d).
Home field is with DAL, which supports the pick.
ContextThe model makes it DAL by 3.2 against a market DAL by 3.5: essentially the same number, so there is little difference to read. The model's total is 63.2 against a line of 52.5: 10.7 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 DAL by 3.2 · market DAL by 3.5
ⓘ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
DAL
Clear advantage
DAL passing ranks #3, PHI defends it at #28; the other way PHI #11 into DAL's #8.
Rushing game
DAL
Clear advantage
DAL rushing ranks #10, PHI defends it at #30; the other way PHI #8 into DAL's #12.
Third down & red zone
DAL
Slight advantage
DAL third-down conversion ranks #1, PHI defends it at #30; the other way PHI #5 into DAL's #15.
Big plays
=
Even
DAL explosive pass rate ranks #11, PHI defends it at #15; the other way PHI #18 into DAL's #19.
Pass protection & rush
DAL
Clear advantage
DAL sack rate ranks #10, PHI defends it at #24; the other way PHI #13 into DAL's #8.
Ball security
DAL
Clear advantage
DAL turnovers / game ranks #6, PHI defends it at #26; the other way PHI #25 into DAL's #13.
Form (last 5)
DAL
Slight advantage
DAL −2.0 per game over the last five, PHI −7.8.
Market
DAL
Clear advantage
Consensus has DAL by 3.5; the model says DAL by 3.2.
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.
3,893 NFL games since 2012
Marginmarket DAL by 3.5 · model DAL by 3.2
Mkt DAL 3.5
Model DAL 3.2
← PHI by 28tieDAL by 28 →
The two numbers sit together; the disagreement is under half a point. Most common margins: 3 (14.5%), 7 (8.6%), 6 (6.7%), 14 (5.1%).
Totalmarket 52.5 · model 63.2
Mkt 52.5
Model 63.2
20 pts4672 pts
17.4% of NFL games finish between 52.5 and 63.2. The league’s median total since 2012 is 45.
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.
