ECAI 2004 Conference Paper

[full paper]

Efficient and Secure Collaborative Filtering through Intelligent Neighbourhood Selection

Michael P. O'Mahony, Neil J. Hurley, Guenole C. M. Silvestre

In this paper, we introduce novel neighbourhood formation and similarity weight transformation schemes for automated collaborative filtering systems. We define profile utility, which models the usefulness of user profiles as a function of the items they contain. For example, item popularity and item rating distribution are two such possible measures of utility. We demonstrate that our approach leads to more efficient collaborative filtering when compared to a benchmark k-nearest neighbour approach, while providing system accuracy and coverage to the same standard. In addition, our new approach is secure against malicious attack as outlined in our previous work.

Keywords: Collaborative Filtering, Efficiency, Security, Robustness, Neighbourhood Selection

Citation: Michael P. O'Mahony, Neil J. Hurley, Guenole C. M. Silvestre: Efficient and Secure Collaborative Filtering through Intelligent Neighbourhood Selection. In R.López de Mántaras and L.Saitta (eds.): ECAI2004, Proceedings of the 16th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2004, pp.383-387.