Diversifying Music Recommendations

We compare submodular and Jaccard methods to diversify Amazon Music recommendations. Submodularity significantly improves recommendation quality and user engagement. Unlike the Jaccard method, our submodular approach incorporates item relevance score within its optimization function, and produces a...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Nassif, Houssam, Kemal Oral Cansizlar, Goodman, Mitchell, Vishwanathan, SVN
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 02.10.2018
Online AccessGet full text

Cover

More Information
Summary:We compare submodular and Jaccard methods to diversify Amazon Music recommendations. Submodularity significantly improves recommendation quality and user engagement. Unlike the Jaccard method, our submodular approach incorporates item relevance score within its optimization function, and produces a relevant and uniformly diverse set.
ISSN:2331-8422