UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Private Distributed Collaborative Filtering Using Estimated Concordance Measures

Lathia, N; Hailes, S; Capra, L; (2007) Private Distributed Collaborative Filtering Using Estimated Concordance Measures. In: RECSYS 07: PROCEEDINGS OF THE 2007 ACM CONFERENCE ON RECOMMENDER SYSTEMS. (pp. 1 - 8). ASSOC COMPUTING MACHINERY

Full text not available from this repository.

Abstract

Collaborative filtering has become an established method to measure users' similarity and to make predictions about their interests. However, prediction accuracy comes at the cost of user's privacy: in order to derive accurate similarity measures, users are required to share their rating history with each other. In this work we propose a new measure of similarity, which achieves comparable prediction accuracy to the Pearson correlation coefficient, and that can successfully be estimated without breaking users' privacy. This novel method works by estimating the number of concordant, discordant and tied pairs of ratings between two users with respect to a shared random set of ratings. In doing so, neither the items rated nor the ratings themselves are disclosed, thus achieving strictly-private collaborative filtering. The technique has been evaluated using the recently released Netflix prize dataset.

Type:Proceedings paper
Title:Private Distributed Collaborative Filtering Using Estimated Concordance Measures
Event:ACM Conference on Recommender Systems
Location:Minneapolis, MN
Dates:2007-10-19 - 2007-10-20
ISBN-13:978-1-59593-730-8
Keywords:Correlation, Privacy, Recommender Systems
UCL classification:UCL > School of BEAMS > Faculty of Engineering Science > Computer Science

Archive Staff Only: edit this record