# Cluster tracks or artist based on user listens : algorithm proposition

**URL:** https://community.metabrainz.org/t/cluster-tracks-or-artist-based-on-user-listens-algorithm-proposition/742325
**Category:** ListenBrainz
**Tags:** recommendations, algorithms, cluster, genres
**Created:** [February 7, 2025, 10:19pm UTC](https://community.metabrainz.org/t/cluster-tracks-or-artist-based-on-user-listens-algorithm-proposition/742325 "2025-02-07T22:19:07Z")
**Posts on this page:** 1
**Showing post:** 3

<div class="post-metadata">

### Author: ![yuioen](https://community.metabrainz.org/letter_avatar_proxy/v4/letter/y/b5e925/32.png) [@yuioen](https://community.metabrainz.org/u/yuioen)
#### Post date: [February 17, 2025, 1:30pm UTC](https://community.metabrainz.org/t/cluster-tracks-or-artist-based-on-user-listens-algorithm-proposition/742325/3 "2025-02-17T13:30:05Z")

</div>

it has nothing to do with genre tags, it’s to group artist/tracks based on listening data, we could consider the result is a genre. But really it’s only statistical relationship.  
This approach is building a group of track, it doesn’t give a relationship between two tracks has it’s the case in [session](https://community.metabrainz.org/t/introducing-the-listenbrainz-session-viewer/598789). Sessions can give a relation with a value that represent how strong is the relation. On the contrary in this case there is not such value. e only know the tracks/artists are in the same group.

---

_[View the full topic](https://community.metabrainz.org/t/cluster-tracks-or-artist-based-on-user-listens-algorithm-proposition/742325)._