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
52%Cleveland BrownsLean
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.
CLE by 0.8market CLE by 1
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.
48.8 pointsmarket 48
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 Cleveland Browns at 52% to win, with the market at CLE by 1.
Quarterback: the pick was locked with Jacoby Brissett starting for Cleveland Browns, and the model prices that in.
CLE has the advantage in passing: CLE passing ranks #16, ATL defends it at #30; the other way ATL #20 into CLE's #11.
Rest: CLE has 3 more days since its last game (ATL 7d, CLE 10d).
Home field is with ATL, which the pick has to overcome.
ContextThe model makes it CLE by 0.8 against a market CLE by 1: essentially the same number, so there is little difference to read. The model's total is 48.8 against a line of 48: 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 CLE by 0.8 · market CLE by 1
ⓘ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
CLE
Clear advantage
CLE passing ranks #16, ATL defends it at #30; the other way ATL #20 into CLE's #11.
Rushing game
ATL
Slight advantage
ATL rushing ranks #3, CLE defends it at #29; the other way CLE #6 into ATL's #25.
Third down & red zone
=
Even
ATL red-zone touchdown rate ranks #15, CLE defends it at #14; the other way CLE #19 into ATL's #17.
Big plays
=
Even
ATL explosive rush rate ranks #9, CLE defends it at #30; the other way CLE #3 into ATL's #18.
Pass protection & rush
CLE
Slight advantage
CLE sack rate ranks #24, ATL defends it at #32; the other way ATL #25 into CLE's #21.
Ball security
=
Even
ATL turnovers / game ranks #10, CLE defends it at #23; the other way CLE #12 into ATL's #25.
Form (last 5)
=
Even
ATL 0.0 per game over the last five, CLE −2.0.
Market
=
Even
Consensus has CLE by 1; the model says CLE 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.
3,893 NFL games since 2012
Marginmarket CLE by 1 · model CLE by 0.8
Mkt CLE 1
Model CLE 0.8
← CLE by 28tieATL by 28 →
The two numbers sit together; the disagreement is under half a point. The market is on 1, a number 4.5% of games land on exactly (a push). Most common margins: 3 (14.5%), 7 (8.6%), 6 (6.7%), 14 (5.1%).
Totalmarket 48 · model 48.8
Mkt 48
Model 48.8
20 pts4672 pts
No whole-number total falls between 48 and 48.8. 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.
