search

spotify-research / cosernn

Code for the paper "Contextual and Sequential User Embeddings for Large-Scale Music Recommendation".
Apache License 2.0
33 stars 9 forks source link

Questions about the experiment dataset in the paper #1

Open L-myth opened 2 years ago

L-myth commented 2 years ago

Hello, I am a student researching contextual and sequential recommendation. I would like to ask whether the dataset opened by Spotify is the same as the dataset in this paper. I found that the public dataset lacks some of the features used in this paper and the time window is different. Would you please provide your experimental dataset for research?

lucasmaystre commented 2 years ago

Hi @L-myth, thank you for your interest in our work. You are correct - the dataset used to produce the results in this paper is different from the one that is publicly available on https://research.atspotify.com/.

Unfortunately we are unable to share the exact data we used in the paper at this time. We strive to make our research reproducible but in this case we could only share the model code.

Wishing you all the best for your research!