Recommendation Algorithm
The system a platform uses to decide which videos to show which viewers, driven mainly by watch signals.
A recommendation algorithm ranks and distributes videos by predicting how much each viewer will engage. Short-form algorithms lean heavily on watch-time signals — hook rate, retention, completion — plus engagement and rewatches, and they test new clips on a small sample before widening reach.
You can't game it, but you can feed it what it rewards: a strong hook and high retention.
Keep reading.
For You Page (FYP)
TikTok's algorithmic main feed that shows videos to people who don't follow you — the primary engine of reach.
Read →Retention (Watch Time)
How much of a video viewers actually watch — the metric short-form algorithms weight most heavily.
Read →Shadowban
An alleged, unannounced suppression of a creator's reach without a formal notice or ban.
Read →Stop reading, start posting.
Turn a long video into ranked, captioned clips — free to start.
Start free →