A reference implemententation of the CoSeRNN model for contextual music recommendation, presented in the following paper:
Casper Hansen, Christian Hansen, Lucas Maystre, Rishabh Mehrotra, Brian Brost, Federico Tomasi, Mounia Lalmas. Contextual and Sequential User Embeddings for Large-Scale Music Recommendation, RecSys 2020.
Our implementation requires Python 3.7 and TensorFlow 1.x. To run the code, you will need a CUDA-enabled GPU.
To get started, simply follow these steps:
- Clone the repo locally with:
git clone https://github.com/spotify-research/cosernn.git - Move to the repository with:
cd cosernn - install the dependencies:
pip install -r requirements.txt - install the package:
pip install -e lib/
Generate data using
python scripts/generate_data.py
Train the CoSeRNN model using
python scripts/train.py path/to/records
Create a new issue
We feel that a welcoming community is important and we ask that you follow Spotify's Open Source Code of Conduct in all interactions with the community.
A full list of contributors can be found on GitHub.
Follow @SpotifyResearch on Twitter for updates.
Copyright 2020 Spotify, Inc.
Licensed under the Apache License, Version 2.0: https://www.apache.org/licenses/LICENSE-2.0
Please report sensitive security issues via Spotify's bug-bounty program (https://hackerone.com/spotify) rather than GitHub.