A recommendation engine suggests items, such as videos, products or apps, that a person is likely to want, based on what they and similar people have liked.
In plain words
Two classic ideas drive it. Content-based filtering recommends items similar to ones you liked, using item features such as category. Collaborative filtering uses patterns across many users, so it can suggest something liked by people with tastes like yours. Large systems work in stages: narrow a huge catalogue to a smaller set of candidates, score and rank them, then re-rank for variety, freshness and fairness.
A quick example
Google's course uses an app store: if you installed several education apps, content-based filtering suggests more education apps, while collaborative filtering might suggest a puzzle game that users with similar installs enjoyed.
Where you'll meet it
- Shopping, streaming and news feeds.
- App stores and online courses.
Related
Sources
- DocsRecommendation systems overview: types, Google for Developers (Machine Learning) · read 29 Sept 2026
- DocsContent-based filtering basics, Google for Developers (Machine Learning) · read 29 Sept 2026
- DocsCollaborative filtering basics, Google for Developers (Machine Learning) · read 29 Sept 2026
Checked by WhatIsAI against the sources above · 29 Sept 2026. Spotted an error? Report it.