Music Recommendation System for Million Song Dataset Challenge
This work addresses music recommendation for users in a large-scale dataset, but it is incremental as it applies an existing collaborative filtering method.
The paper tackled the Million Song Dataset challenge by predicting missing listening history for 110,000 users based on full histories of 1 million users, achieving a MAP@500 score of 0.15037 and placing 8th in the competition.
In this paper a system that took 8th place in Million Song Dataset challenge is described. Given full listening history for 1 million of users and half of listening history for 110000 users participatints should predict the missing half. The system proposed here uses memory-based collaborative filtering approach and user-based similarity. MAP@500 score of 0.15037 was achieved.