Playlist prediction via metric embedding

DMCA

Playlist prediction via metric embedding (2012)

Cached

Download Links

by Shuo Chen , Joshua L. Moore , Douglas Turnbull , Thorsten Joachims

Venue:	In Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining
Citations:	14 - 4 self

BibTeX

@INPROCEEDINGS{Chen12playlistprediction,
    author = {Shuo Chen and Joshua L. Moore and Douglas Turnbull and Thorsten Joachims},
    title = {Playlist prediction via metric embedding},
    booktitle = {In Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining},
    year = {2012},
    pages = {714--722},
    publisher = {ACM}
}

OpenURL

Abstract

Digital storage of personal music collections and cloud-based music services (e.g. Pandora, Spotify) have fundamentally changed how music is consumed. In particular, automati-cally generated playlists have become an important mode of accessing large music collections. The key goal of automated playlist generation is to provide the user with a coherent lis-tening experience. In this paper, we present Latent Markov Embedding (LME), a machine learning algorithm for gen-erating such playlists. In analogy to matrix factorization methods for collaborative filtering, the algorithm does not require songs to be described by features a priori, but it learns a representation from example playlists. We formu-late this problem as a regularized maximum-likelihood em-bedding of Markov chains in Euclidian space, and show how the resulting optimization problem can be solved efficiently. An empirical evaluation shows that the LME is substantially more accurate than adaptations of smoothed n-gram models commonly used in natural language processing.

Keyphrases

playlist prediction key goal personal music collection smoothed n-gram model digital storage generated playlist automated playlist generation latent markov embedding markov chain factorization method example playlist cloud-based music service natural language processing coherent lis-tening experience machine learning algorithm optimization problem gen-erating playlist euclidian space collaborative filtering empirical evaluation show large music collection regularized maximum-likelihood em-bedding important mode

DMCA