Web-scale media recommendation systems

Gideon Dror*, Noam Koenigstein, Yehuda Koren

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


Modern consumers are inundated with choices. A variety of products are offered to consumers, who have unprecedented opportunities to select products that meet their needs. The opportunity for selection also presents a time-consuming need to select. This has led to the development of recommender systems that direct consumers to products expected to satisfy them. One area in which such systems are particularly useful is that of media products, such as movies, books, television, and music. We study the details of media recommendation by focusing on a large scale music recommender system. To this end, we introduce a music rating data set that is likely to be the largest of its kind, in terms of both number of users, items, and total number raw ratings. The data were collected by Yahoo! Music over a decade. We formulate a detailed recommendation model, specifically designed to account for the data set properties, its temporal dynamics, and the provided taxonomy of items. The paper demonstrates a design process that we believe to be useful at many other recommendation setups. The process is based on gradual modeling of additive components of the model, each trying to reflect a unique characteristic of the data.

Original languageEnglish
Article number6209384
Pages (from-to)2722-2736
Number of pages15
JournalProceedings of the IEEE
Issue number9
StatePublished - 2012
Externally publishedYes


  • Collaborative filtering
  • Yahoo! Music
  • matrix factorization
  • recommender systems


Dive into the research topics of 'Web-scale media recommendation systems'. Together they form a unique fingerprint.

Cite this