Chapter

E-Commerce and Web Technologies

Volume 3590 of the series Lecture Notes in Computer Science pp 98-107

A Collaborative Filtering Recommendation Methodology for Peer-to-Peer Systems

  • Hyea Kyeong KimAffiliated withSchool of Business Administration, KyungHee University
  • , Jae Kyeong KimAffiliated withSchool of Business Administration, KyungHee University
  • , Yoon Ho ChoAffiliated withSchool of E-Business, KookMin University

* Final gross prices may vary according to local VAT.

Get Access

Abstract

To deal with the image recommending problems in P2P systems, this paper proposes a PeerCF-CB (Peer oriented Collaborative Filtering recommendation methodology using Contents-Based filtering). PeerCF-CB uses recent ratings of peers to adopt a change in peer preferences, and searches for nearest peers with similar preference through peer-based local information only. The performance of PeerCF-CB is evaluated with real transaction data in S content provider. Our experimental result shows that PeerCF-CB offers not only remarkably higher quality of recommendations but also dramatically faster performance than the centralized collaborative filtering recommendation systems.