Solutions of the KSI CUNI.CZ team for the RecSys Challenge 2018
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.


Solutions of the KSI CUNI.CZ team for the RecSys Challenge 2018


  • Python 3, tensorFlow, numpy, pandas, scikit-learn

High-level overview

  • our team participated mainly in the creative track of the RecSys Challenge 2018. As additional dataset, we utilized audio features of the tracks as collected through Spotify Audio API: (see

  • furthermore the solution consisted mainly of Word2Vec models applied on both track-level and album-level (see for sentences preparation and and for model creations). Word2Vec models are utilized by output model ( in the form of pre-calculated top-k most similar tracks/albums for each challenge set track.

  • audio features are standardized (AudioFeaturesVisualization.ipynb), processed via Siamese network ( and utilized according to their stability w.r.t. playlist (calculated in to re-rank recommended tracks and also to recommend additional tracks should the overall stability be high.

  • output model further utilizes tracks from/with the same album/author/title and overall popularity of tracks. Datasets for these calculations are generated by

  • note that word2vec model generation is nondeterministic due to the top-k words selection. Ask authors for stored models used for generating solutions.


  • TBD