lbdeoliveira/song-playlist-recommendation

This project was a joint effort by Lucas De Oliveira, Chandrish Ambati, and Anish Mukherjee to create a song and playlist embeddings for recommendations in a distributed fashion using a 1M playlist dataset by Spotify.

41
/ 100
Emerging

This project helps music streaming platforms or music recommendation services suggest new songs or entire playlists. By analyzing millions of existing user-curated playlists, it takes a playlist as input and recommends similar songs or other playlists. This tool is useful for data scientists or engineers working at music streaming companies who need to build scalable recommendation systems.

214 stars. No commits in the last 6 months.

Use this if you need to build a music recommendation system that scales to billions of playlists, leveraging existing playlist data to understand song and playlist similarities.

Not ideal if you're looking for a simple, in-memory solution for a small dataset, or if your recommendation strategy isn't primarily based on user-curated playlist co-occurrence.

music-streaming playlist-curation song-recommendation content-discovery large-scale-recommendations
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 23 / 25

How are scores calculated?

Stars

214

Forks

64

Language

HTML

License

Last pushed

May 18, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/lbdeoliveira/song-playlist-recommendation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.