Typicality-based collaborative filtering recommendation

Y. Cai, H.-F. Leung, Qing Li, H. Min, J. Tang, J. Li

Research output: Journal article publicationJournal articleAcademic researchpeer-review

138 Citations (Scopus)

Abstract

Collaborative filtering (CF) is an important and popular technology for recommender systems. However, current CF methods suffer from such problems as data sparsity, recommendation inaccuracy, and big-error in predictions. In this paper, we borrow ideas of object typicality from cognitive psychology and propose a novel typicality-based collaborative filtering recommendation method named TyCo. A distinct feature of typicality-based CF is that it finds 'neighbors' of users based on user typicality degrees in user groups (instead of the corated items of users, or common users of items, as in traditional CF). To the best of our knowledge, there has been no prior work on investigating CF recommendation by combining object typicality. TyCo outperforms many CF recommendation methods on recommendation accuracy (in terms of MAE) with an improvement of at least 6.35 percent in Movielens data set, especially with sparse training data (9.89 percent improvement on MAE) and has lower time cost than other CF methods. Further, it can obtain more accurate predictions with less number of big-error predictions. © 2014 IEEE.
Original languageEnglish
Article number6407132
Pages (from-to)766-779
Number of pages14
JournalIEEE Transactions on Knowledge and Data Engineering
Volume26
Issue number3
DOIs
Publication statusPublished - 1 Mar 2014
Externally publishedYes

Keywords

  • Collaborative filtering
  • Recommendation
  • Typicality

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this