Beyond collaborative filtering: The list recommendation problem

Oren Sar Shalom, Noam Koenigstein, Ulrich Paquet, Hastagiri P. Vanchinathan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

35 Scopus citations


Most Collaborative Filtering (CF) algorithms are optimized using a dataset of isolated user-item tuples. However, in commercial applications recommended items are usually served as an ordered list of several items and not as isolated items. In this setting, inter-item interactions have an effect on the list's Click-Through Rate (CTR) that is unaccounted for using traditional CF approaches. Most CF approaches also ignore additional important factors like click propensity vari-ation, item fatigue, etc. In this work, we introduce the list recommendation problem. We present useful insights gleaned from user behavior and consumption patterns from a large scale real world recommender system. We then pro-pose a novel two-layered framework that builds upon ex-isting CF algorithms to optimize a list's click probability. Our approach accounts for inter-item interactions as well as additional information such as item fatigue, trendiness patterns, contextual information etc. Finally, we evaluate our approach using a novel adaptation of Inverse Propensity Scoring (IPS) which facilitates off-policy estimation of our method's CTR and showcases its effectiveness in real-world settings.

Original languageEnglish
Title of host publication25th International World Wide Web Conference, WWW 2016
PublisherInternational World Wide Web Conferences Steering Committee
Number of pages10
ISBN (Electronic)9781450341431
StatePublished - 2016
Event25th International World Wide Web Conference, WWW 2016 - Montreal, Canada
Duration: 11 Apr 201615 Apr 2016

Publication series

Name25th International World Wide Web Conference, WWW 2016


Conference25th International World Wide Web Conference, WWW 2016


  • Click prediction
  • Collaborative Filtering


Dive into the research topics of 'Beyond collaborative filtering: The list recommendation problem'. Together they form a unique fingerprint.

Cite this