Home // IMMM 2015, The Fifth International Conference on Advances in Information Mining and Management // View article

Robustness of Bisecting k-means Clustering-based Collaborative Filtering Algorithm

Authors:
Alper Bilge
Huseyin Polat

Keywords: robustness; shilling; clustering; recommendation

Abstract:
The unprecedented popularity of e-shopping amenities provided by online retailers escalates attention to recommendation facilities. Collaborative filtering is one of the well-known recommendation techniques that helps customers choose possible products of interest by automating word-of-mouth habits. However, due to their nature, recommendation algorithms are open to shilling attacks of malicious users to promote/demote certain products. We propose bisecting k-means clustering-based recommendation algorithm as a robust algorithm in non-private environments against well-known shilling attacks. We investigate its robustness against shilling attacks by performing real databased experiments. We also analyze the effects of varying attacking parameters. We empirically establish that the algorithm is resilient against shilling attacks without significantly influenced by malicious profiles.

Pages: 7 to 13

Copyright: Copyright (c) IARIA, 2015

Publication date: June 21, 2015

Published in: conference

ISSN: 2326-9332

ISBN: 978-1-61208-415-2

Location: Brussels, Belgium

Dates: from June 21, 2015 to June 26, 2015