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
66%Baltimore RavensSolid
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.
BAL by 5.7market BAL by 4.5
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.
39.9 pointsmarket 44
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 Baltimore Ravens at 66% to win, with the market at BAL by 4.5.
Quarterback: the pick was locked with Patrick Mahomes starting for Kansas City Chiefs, and the model prices that in.
BAL has the advantage in rushing: BAL rushing ranks #3, KC defends it at #25; the other way KC #23 into BAL's #14.
Counterpoint: sack rate favours KC. KC sack rate ranks #2, BAL defends it at #7; the other way BAL #23 into KC's #4. The pick still lands on BAL because it rests on the whole season's results and the market's price, not one area.
Home field is with BAL, which supports the pick.
ContextThe model makes it BAL by 5.7 against a market BAL by 4.5: 1.2 points of daylight in BAL's favour. The model's total is 39.9 against a line of 44: 4.1 points below 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 BAL by 5.7 · market BAL by 4.5
ⓘ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
KC passing ranks #7, BAL defends it at #2; the other way BAL #10 into KC's #4.
Rushing game
BAL
Clear advantage
BAL rushing ranks #3, KC defends it at #25; the other way KC #23 into BAL's #14.
Third down & red zone
=
Even
BAL red-zone touchdown rate ranks #6, KC defends it at #8; the other way KC #20 into BAL's #2.
Big plays
=
Even
BAL explosive rush rate ranks #5, KC defends it at #6; the other way KC #23 into BAL's #21.
Pass protection & rush
KC
Clear advantage
KC sack rate ranks #2, BAL defends it at #7; the other way BAL #23 into KC's #4.
Ball security
BAL
Clear advantage
BAL turnovers / game ranks #16, KC defends it at #23; the other way KC #23 into BAL's #9.
Form (last 5)
BAL
Slight advantage
BAL +12.2 per game over the last five, KC +6.6.
Market
BAL
Clear advantage
Consensus has BAL by 4.5; the model says BAL by 5.7.
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 BAL by 4.5 · model BAL by 5.7
Mkt BAL 4.5
Model BAL 5.7
← KC by 28tieBAL by 28 →
2.0% of NFL games land between the two numbers. Most common margins: 3 (14.5%), 7 (8.6%), 6 (6.7%), 14 (5.1%).
Totalmarket 44 · model 39.9
Mkt 44
Model 39.9
20 pts4672 pts
12.1% of NFL games finish between 44 and 39.9. 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.
