Skip to content

Latest commit

 

History

History
9 lines (8 loc) · 477 Bytes

File metadata and controls

9 lines (8 loc) · 477 Bytes

CSCE-670-Playlist-Recommender-System

In this project we have implemented an ensembled approach to build a song recommender system. For a given user, we try to recommend a playlist to the user in the order of expected preference. We do this by using the principles of song popularity, user to user similarity, neural methods, and Bayesian Personalized Ranking. For our recommendation system, we use implicit information retrieved using song listen count for a user-song pair