Skip to content
BENIBIX Learn

Recommendation System

Also known as Recommender System, Recommendation Engine, Recommender

A system that guesses what you will like next. It learns from what you and others chose.

Think of it like

Think of it like a shop owner who knows you. 'You liked that one, so try this.'

Example

Lucy watches three space films on a streaming app. People who watched the same three also loved a fourth, so the app puts it at the top of her screen.

Why it matters

It decides much of what people see online. For many shops and apps it drives a large share of sales and viewing.

Definition

A recommendation system suggests things a person is likely to want, like films, songs or products. It learns from what people watched, bought, rated or skipped. One way finds people with taste like yours and suggests what they liked. Another finds things like the ones you already liked. Most big apps use both.
The empty box is a film one person has not seen. The system fills in a guess from people with similar ratings.

Common mistake

Only ever suggesting more of the same. Users get bored, so good systems mix in some new things too.

Key takeaways

  1. 1
    Learns from choices. Watched, bought, rated, skipped.
  2. 2
    Similar people. Or similar items.
  3. 3
    Shapes what you see. Drives much of online life.

Learn it properly