Frequently asked questions
How accurate are NFL game predictions?
The best public forecast, the market's final price, picks the winner of about 66–67% of NFL games. Good statistical models land between 63% and 67%. Ours picked 65.0% over 4,146 regular-season games from 2010 to 2025 in a walk-forward backtest, and the live record is published every week. Nobody sustains 70%; a single 17-game season swings several points on luck alone.
Is this a tip?
No. Predictions are published to show whether the method works, and every one is graded in public. We never tell anyone what to do with a pick, no link here pays us, and our own analysis found no edge over the market's final price. Please treat the numbers as a study, not a tip.
Does the site make money from any of this?
Not from you. There are no ads, no referral or affiliate links and no paid picks. We are independent and paid for by Nifti Mobility Group.
Can I see the picks before the games?
Yes. Picks are stored before kickoff, with the probability and a plain-language reason, and the page shows them as soon as they exist, usually a week ahead. The final version is the last one stored before kickoff; the What Moved panel shows how it changed on the way there.
Where does the data come from?
Schedules, results, play-by-play, injury reports and depth charts come from the open-source nflverse project (CC-BY-4.0). The market's final price comes from the nflverse schedule feed. News comes from public RSS feeds. Weather comes from the National Weather Service. Nothing is paid for and nothing is scraped from behind a login.
Does the model use the market's price?
Never as an input. The market's final price is stored and shown only as the benchmark to grade against. That is deliberate: a model that copies the market cannot tell you anything the market does not.
Why do the projected scores look so similar?
Because a projection is the middle of a wide range. Real NFL scores vary by about ten points per team from game to game, but the most likely score for most games is somewhere near 21–27. A model that projected wild scores would be less accurate, not more. The win probability carries the real information; the score is a companion.
How is the model different from the market?
It agrees with the market on the pick about 87% of the time, because both are looking at the same teams. When the two disagree, history says the market is right more often (about 56–44). We publish those disagreements rather than hide them; they are the interesting games.
What does the AI do here?
Two things, and we want to be clear about both. First, AI helped build this: the code, the pages and much of the writing were produced with an AI assistant (Anthropic's Claude) working alongside a human owner who set the goals, made the decisions and checked the results. Second, AI runs one step of the weekly process: a language model reads news reports and turns them into structured, capped claims (for example, a quarterback change the schedule data has not caught up with). What AI does not do is make the predictions. Those come from ordinary statistics — regressions on team efficiency, quarterback play, injuries and rest — that we can explain step by step. Every AI-produced claim is logged with its source, limited to a few points, and graded afterwards, so you can see exactly what it changed and whether that helped.
How often does it update?
Four times a day, plus extra runs on Sundays before the early, late and night games so inactives are counted. Each run refreshes the data, grades finished games, reads the news, re-predicts and rebuilds the rankings and season projections.
Why did a pick change during the week?
Usually because the named starting quarterback changed, the injury report changed, or a news item passed the analyst layer's filters. The What Moved panel on each week's page lists every change with the biggest reason. Nothing changes after kickoff.
What about player rankings and player predictions?
The Players page ranks quarterbacks, running backs, receivers and tight ends from play-by-play data: expected points added per touch, adjusted for the defenses faced, weighted toward recent games and shrunk so a few big plays do not outrank a full season. Linemen and defenders are not ranked because free data gives them no per-play credit, and we would rather say so than invent a number. These rankings are not inputs to the game predictions; whether they should be is a study on our list. We do not predict individual player stats.
Who makes this?
NFL is made by Nifti Mobility Group in Biddeford, Maine. It grew out of an NBA model built the same way, and both are published to show whether a careful, honest method works over time.
Follow your team. It's free.
Your team on top of every page, with its next game and our pick. Want more? Plus from US$7/mo, 7 days free.