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
74%Los Angeles RamsStrong
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.
LAR by 8.7market LAR by 10.5
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.
46.9 pointsmarket 46.5
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 Los Angeles Rams at 74% to win, with the market at LAR by 10.5.
Quarterback: the pick was locked with Matthew Stafford starting for Los Angeles Rams, and the model prices that in.
LAR has the advantage in third downs and the red zone: LAR red-zone touchdown rate ranks #17, ATL defends it at #17; the other way ATL #15 into LAR's #1.
Rest: LAR has 3 more days since its last game (LAR 10d, ATL 7d).
Home field is with LAR, which supports the pick.
ContextThe model makes it LAR by 8.7 against a market LAR by 10.5: 1.8 points of daylight in ATL's favour. The model's total is 46.9 against a line of 46.5: 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 LAR by 8.7 · market LAR by 10.5
ⓘ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
=
Even
ATL passing ranks #20, LAR defends it at #25; the other way LAR #30 into ATL's #30.
Rushing game
=
Even
ATL rushing ranks #3, LAR defends it at #12; the other way LAR #18 into ATL's #25.
Third down & red zone
LAR
Slight advantage
LAR red-zone touchdown rate ranks #17, ATL defends it at #17; the other way ATL #15 into LAR's #1.
Big plays
=
Even
LAR explosive pass rate ranks #27, ATL defends it at #25; the other way ATL #18 into LAR's #10.
Pass protection & rush
LAR
Slight advantage
LAR sack rate ranks #31, ATL defends it at #32; the other way ATL #25 into LAR's #19.
Ball security
ATL
Slight advantage
ATL turnovers / game ranks #10, LAR defends it at #18; the other way LAR #23 into ATL's #25.
Form (last 5)
=
Even
LAR +0.4 per game over the last five, ATL 0.0.
Market
LAR
Clear advantage
Consensus has LAR by 10.5; the model says LAR by 8.7.
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 LAR by 10.5 · model LAR by 8.7
Mkt LAR 10.5
Model LAR 8.7
← ATL by 28tieLAR by 28 →
3.8% of NFL games land between the two numbers. Most common margins: 3 (14.5%), 7 (8.6%), 6 (6.7%), 14 (5.1%).
Totalmarket 46.5 · model 46.9
Mkt 46.5
Model 46.9
20 pts4672 pts
Model and market agree on the total to within half a point. 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.
