Multi-product utility maximization for economic recommendation

Qi Zhao, Yongfeng Zhang, Yi Zhang, Daniel Friedman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Scopus citations

Abstract

Basic economic relations such as substitutability and com- plementarity between products are crucial for recommenda- tion tasks, since the utility of one product may depend on whether or not other products are purchased. For example, the utility of a camera lens could be high if the user pos- sesses the right camera (complementarity), while the utility of another camera could be low because the user has already purchased one (substitutability). We propose multi-product utility maximization (MPUM) as a general approach to rec- ommendation driven by economic principles. MPUM inte- grates the economic theory of consumer choice with person- alized recommendation, and focuses on the utility of sets of product sets for individual users. MPUM considers what the users already have when recommending additional products. We evaluate MPUM against several popular recommenda- tion algorithms on two real-world E-commerce datasets. Re- sults confirm the underlying economic intuition, and show that MPUM significantly outperforms the comparison algo- rithms under top-K evaluation metrics.

Original languageEnglish (US)
Title of host publicationWSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining
PublisherAssociation for Computing Machinery, Inc
Pages435-443
Number of pages9
ISBN (Electronic)9781450346757
DOIs
StatePublished - Feb 2 2017
Externally publishedYes
Event10th ACM International Conference on Web Search and Data Mining, WSDM 2017 - Cambridge, United Kingdom
Duration: Feb 6 2017Feb 10 2017

Publication series

NameWSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining

Other

Other10th ACM International Conference on Web Search and Data Mining, WSDM 2017
Country/TerritoryUnited Kingdom
CityCambridge
Period2/6/172/10/17

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Information Systems
  • Computer Networks and Communications
  • Software

Keywords

  • Collaborative filtering
  • Computational economics
  • Recommender systems
  • Utility maximization

Fingerprint

Dive into the research topics of 'Multi-product utility maximization for economic recommendation'. Together they form a unique fingerprint.

Cite this