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%Pittsburgh SteelersLean
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.
PIT by 3.1market PIT 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.
42.3 pointsmarket 43.5
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 Pittsburgh Steelers at 59% to win, with the market at PIT by 2.5.
PIT has the advantage in big plays: PIT explosive pass rate ranks #8, DAL defends it at #22; the other way DAL #25 into PIT's #15.
PIT has the advantage in rushing: PIT rushing ranks #22, DAL defends it at #31; the other way DAL #27 into PIT's #19.
Counterpoint: sack rate favours DAL. DAL sack rate ranks #9, PIT defends it at #20; the other way PIT #27 into DAL's #2. The pick still lands on PIT because it rests on the whole season's results and the market's price, not one area.
Rest: DAL has 3 more days since its last game (PIT 7d, DAL 10d).
Form: DAL has the better last five games by 7.8 points a game (PIT -13.2, DAL -5.4).
Home field is with PIT, which supports the pick.
ContextThe model makes it PIT by 3.1 against a market PIT by 2.5: essentially the same number, so there is little difference to read. The model's total is 42.3 against a line of 43.5: 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 PIT by 3.1 · market PIT 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
PIT
Clear advantage
PIT passing ranks #18, DAL defends it at #16; the other way DAL #30 into PIT's #12.
Rushing game
PIT
Clear advantage
PIT rushing ranks #22, DAL defends it at #31; the other way DAL #27 into PIT's #19.
Third down & red zone
PIT
Slight advantage
PIT red-zone touchdown rate ranks #29, DAL defends it at #32; the other way DAL #31 into PIT's #13.
Big plays
PIT
Clear advantage
PIT explosive pass rate ranks #8, DAL defends it at #22; the other way DAL #25 into PIT's #15.
Pass protection & rush
DAL
Clear advantage
DAL sack rate ranks #9, PIT defends it at #20; the other way PIT #27 into DAL's #2.
Ball security
PIT
Clear advantage
PIT turnovers / game ranks #8, DAL defends it at #13; the other way DAL #28 into PIT's #5.
Form (last 5)
DAL
Clear advantage
PIT −13.2 per game over the last five, DAL −5.4.
Market
PIT
Slight advantage
Consensus has PIT by 2.5; the model says PIT by 3.1.
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 PIT by 2.5 · model PIT by 3.1
Mkt PIT 2.5
Model PIT 3.1
← DAL by 28tiePIT by 28 →
7.7% of NFL games land between the two numbers. The model’s number is across the key number 3. Most common margins: 3 (14.5%), 7 (8.6%), 6 (6.7%), 14 (5.1%).
Totalmarket 43.5 · model 42.3
Mkt 43.5
Model 42.3
20 pts4672 pts
3.5% of NFL games finish between 43.5 and 42.3. 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.