Twitters recommendation algorithm aims to distill 500 million daily tweets to a handful of top tweets that will show on a users timeline. It is composed of interconnected services and jobs with a set of core models and features that extract latent information from tweet, user, and engagement data to deliver more relevant recommendations. The recommendation pipeline is made up of three main stages, and the service responsible for constructing and serving the For You timeline is called Home Mixer. This blog post provides an introduction to how the algorithm selects Tweets for your timeline, including retrieving candidates from various sources, In-Network Source, Out-of-Network Source, Real Graph, Candidate Scoring, and much more. The post will focus on the home timeline’s For You feed and is a valuable resource for anyone who wants to understand Twitter’s recommendation algorithm.
