A hybrid two-stage recommender system for automatic playlist continuation

Abstract

In this paper, we provide the solution for RecSys Challenge 2018 by our Avito team, which obtained the 3rd place in main track. The goal of the competition was to recommend music tracks for automatic playlist continuation. As a part of this challenge, Spotify released a large public dataset, which allowed us to train a rather complex algorithm. Our approach consists of two stages: collaborative filtering for candidate selection and gradient boosting for final prediction. The combination of these two models performed well with the playlist and track metadata given.