Spotify sometimes evokes the old Arthur C. Clarke adage that any sufficiently advanced technology is indistinguishable from magic. Take its Discovery Weekly playlist that it serves up to users, a bespoke collection of 30 songs that Spotify thinks you’ll really, really dig.
Cool. But how does it work? Hackernoon explains everything.
[H]ow does Spotify come up with their magic engine, which seems to nail individual users’ tastes so much more accurately than any of the other services?
Spotify’s 3 Types of Recommendation Models
Spotify actually doesn’t use a single revolutionary recommendation model — instead, they mix together some of the best strategies used by other services to create its own uniquely powerful Discovery engine.
To create Discover Weekly, there are three main types of recommendation models that Spotify employs:
- Collaborative Filtering models (i.e. the ones that Last.fm originally used), which work by analyzing your behavior and others’ behavior.
- Natural Language Processing (NLP) models, which work by analyzing text.
- Audio models, which work by analyzing the raw audio tracks themselves.
That’s just the basics. You need to keep reading.