IWWS: A reliability-based WWW collaborative recommender system

Abstract

Recommender systems using collaborative filtering are a popular technique for reducing information overload and finding products. In this paper, we present a reliability-based WWW collaborative recommender system IWWS (Intelligent Web Wizard System), mainly aiming to attack so-called "Matchmaker" problem in collaborative filtering. The "Matchmaker" problem stems from false assumptions that users are counted only by their similarity and high similarity means good advisers. In order to find good advisers for every user, we construct a matchmaker's reliability mode based on the algorithm deriving from Hits, and apply it in IWWS. Comparative experimental results also show that IWWS contrastively improves performance. © Springer-Verlag Berlin Heidelberg 2005.