Title | ||
---|---|---|
Automatic Music Playlist Continuation via Neighbor-based Collaborative Filtering and Discriminative Reweighting/Reranking |
Abstract | ||
---|---|---|
The focus of RecSys Challenge 2018 is automatic playlist continuation (APC), which refers to the task of adding one or more tracks to a playlist in a manner that does not alter the intended characteristics of the original playlist. This paper presents our approach to this challenge. We adopted neighbor-based collaborative filtering approaches since they are able to deal with large datasets in an efficient and effective way, and have previously been shown to perform well on recommendation problems with similar characteristics. We show that by choosing an appropriate similarity function that properly accounts for the list-song similarities, simple neighbor-based methods can still achieve highly competitive performance on the MPD data, meanwhile, by using a set of techniques that discriminantly finetune the recommendation lists produced by neighbor-based methods, the overall recommendation accuracy can be improved significantly. By using the proposed approach, our team HAIR was able to attain the 6th place in the competition. We have open-sourced our implementation on https://github.com/LauraBowenHe/Recsys-Spotify-2018-challenge.
|
Year | DOI | Venue |
---|---|---|
2018 | 10.1145/3267471.3267481 | RecSys Challenge |
Keywords | Field | DocType |
Music recommender systems, automatic playlist continuation (APC), RecSys challenge | Collaborative filtering,Computer science,Continuation,Artificial intelligence,Discriminative model,Machine learning | Conference |
ISBN | Citations | PageRank |
978-1-4503-6586-4 | 1 | 0.35 |
References | Authors | |
19 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lin Zhu | 1 | 5 | 12.19 |
Bowen He | 2 | 2 | 1.04 |
Mengxin Ji | 3 | 3 | 1.06 |
Ju, Cheng | 4 | 15 | 1.22 |
Yihong Chen | 5 | 2 | 1.38 |