TrailMix: An Ensemble Recommender System for Playlist Curation and Continuation Conference Paper

abstract

• 2018 Association for Computing Machinery. This paper describes TrailMix, an ensemble model designed to tackle the RecSys Challenge 2018 for automatic music playlist continuation. TrailMix combines three different models designed to exploit complementary aspects of playlist recommendation: (i) CC-Title, a cluster-based approach for playlist titles; (ii) DNCF, an extension of Neural Collaborative Filtering for taking advantage of the flat interaction among tracks; and (iii) C-Tree, a hierarchical approach akin to Phylogenetic trees for finding relationships between tracks.

name of conference

• Proceedings of the ACM Recommender Systems Challenge 2018

authors

• Caverlee, James

published proceedings

• RECSYS CHALLENGE'18: PROCEEDINGS OF THE ACM RECOMMENDER SYSTEMS CHALLENGE 2018

altmetric score

• 1

author list (cited authors)

• Zhao, X., Song, Q., Caverlee, J., & Hu, X.

citation count

• 4

complete list of authors

• Zhao, Xing||Song, Qingquan||Caverlee, James||Hu, Xia

publication date

• October 2018

publisher

• Association for Computing Machinery (ACM)  Publisher

keywords

• Collaborative Filtering
• Constructed Tree Comparison
• Neural Network
• Playlist Continuation
• Recommender System

Digital Object Identifier (DOI)

• 10.1145/3267471.3267479

International Standard Book Number (ISBN) 13

• 9781450365864

start page

• 1

end page

• 6

URL

• https://doi.org/10.1145/3267471