How to Movie: What to Watch

About this app

Know how you'll feel about a film before you press play. How to Movie predicts how you will rate a film, using a personal model trained only on your own ratings, never the crowd's average. Rate what you have seen, and every film on your watchlist gets a verdict calibrated to how you actually rate: Ugh, Good, or Great. Not a generic 7.5. A model that is only about you Recent favorites count for more, so predictions keep pace with how your taste actually shifts. What you'll skip is learned from every film you have ever rated; what you'll love, from your recent taste, because that is the half that ages. Your Taste Profile See who you are as a viewer: your signature genre combinations, the people driving your recent taste, where your taste is heading lately, and where you disagree with the crowd. A watchlist that earns its place Every film on it already has a verdict. Filter by decade or release year, see what is out now, and put your next film on the Home Screen with the Next Up widget. Rankings and stats Your favorite actors, directors, studios, genres, and eras, ranked by your own ratings. You already knew you disagree with the critics. This is the proof. Year in Review A shareable, image-rich recap of your movie year, plus a seven-year "Your Era" retrospective. Optional AI Discovery AI recommendations read your taste profile and surface films worth your night, and only when you turn them on, using your own key. Private by design. Your ratings and any AI keys stay on your device. No ads, no analytics SDKs, no tracking. Free to use. How to Movie uses the TMDb API but is not endorsed or certified by TMDb.

The Good+ bar on a prediction card was showing the odds backwards. If it said a film was 20% to be good, it meant 80%. The verdict beside it was right the whole time, so the two disagreed on exactly the films where it mattered most. Fixed, and the bar now stays quiet when your library is too small to support that number. Your predictions now come from one model instead of two. The old split trained separate models for older and newer films, and measuring it properly showed the split was helping neither. One model, trained on everything, is better at both. The widgets now do more than one thing. Coming Soon counts down to watchlist films that have not come out yet, Insight puts what the app noticed about your taste on your home screen, and Next Up can be pinned to only the films it thinks you will love. There are lock screen widgets for the first time. Scores read better too. Where the app holds your rating up against everyone else's it uses IMDb, and where it is simply telling you what a film scored it shows TMDb again, so indie and foreign titles no longer come up blank. Building your model no longer fails if you have rated a film that is still on your watchlist. Re-adding something you have already seen, because you want to watch it again, is a perfectly ordinary thing to do, and it was stopping the build outright. Smaller things: the model's own accuracy numbers are honest out-of-sample figures rather than in-sample ones, the model card on your Home screen now tells you how much better than chance its picks are instead of a bare accuracy percentage, the first tap into a search box no longer stalls, score badges stay readable on any poster art, and Support and Privacy now open the website.

Momentum comes from crawler snapshots for the tracked storefront. “Viral growth signal” means unusually fast recent rating gains; it is an indicator, not download data.

1. First observed Sep 13, 2026 · 2:48 AM Free