Hybrid recommendation for sparse rating matrix: A heterogeneous information network approach

Haiyang Zhang, Ivan Ganchev, Nikola S. Nikolov, Zhanlin Ji, Mairtin O'Droma

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

10 Citations (Scopus)

Abstract

Exploiting additional item meta-data is proposed in this paper for solving data sparsity and cold start problems found in item-based collaborative filtering (CF) techniques, which are employed in recommendation systems. Additional item meta-data provides the foundation for generating a heterogeneous information network (HIN). The proposed approach is to enrich the item-based CF with diverse types of relationships existing between items in the HIN, to overcome the sparsity issue from implicit user feedback. Bayesian personalized ranking optimization technique is used for estimation and its performance is evaluated by comparing the results with the traditional item-based CF. The experimental tests prove that the proposed approach achieves better accuracy.

Original languageEnglish
Title of host publicationProceedings of 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017
EditorsBing Xu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages740-744
Number of pages5
ISBN (Electronic)9781467389778
DOIs
Publication statusPublished - 29 Sept 2017
Externally publishedYes
Event2nd IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017 - Chongqing, China
Duration: 25 Mar 201726 Mar 2017

Publication series

NameProceedings of 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017

Conference

Conference2nd IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017
Country/TerritoryChina
CityChongqing
Period25/03/1726/03/17

Keywords

  • Bayesian personalized ranking
  • Collaborative filtering
  • Heterogeneous information network
  • Meta-path
  • Recommendation system

Cite this