Matrix Factorization Enriched with Item Features

Haiyang Zhang, Ivan Ganchev, Nikola S. Nikolov

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

Abstract

This paper1 presents a novel matrix factorization (MF) recommendation model, FeatureMF, which extends item latent vectors with item representation learned from metadata. By taking into account item features, the model addresses the cold-start item problem and data-sparsity problem of collaborative filtering (CF). Extensive experiments conducted on a public dataset with two testing views confirm that FeatureMF achieves better prediction accuracy than some of the popular state-of-the-art MF-based recommendation models.

Original languageEnglish
Title of host publicationProceedings - 2nd International Conference on Mathematics and Computers in Science and Engineering, MACISE 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages77-80
Number of pages4
ISBN (Electronic)9781728166957
DOIs
Publication statusPublished - Jan 2020
Event2nd International Conference on Mathematics and Computers in Science and Engineering, MACISE 2020 - Madrid, Spain
Duration: 18 Jan 202020 Jan 2020

Publication series

NameProceedings - 2nd International Conference on Mathematics and Computers in Science and Engineering, MACISE 2020

Conference

Conference2nd International Conference on Mathematics and Computers in Science and Engineering, MACISE 2020
Country/TerritorySpain
CityMadrid
Period18/01/2020/01/20

Keywords

  • cold start
  • collaborative filtering (CF)
  • data sparsity
  • matrix factorization (MF)
  • recommendation model

Fingerprint

Dive into the research topics of 'Matrix Factorization Enriched with Item Features'. Together they form a unique fingerprint.

Cite this