(Partial) user preference similarity as classification-based model similarity

Issue title: Inductive Reasoning and Machine Learning for the Semantic Web

Article type: Research Article

Authors: Bouza, Amancio^; | Bernstein, Abraham

Affiliations: Department of Informatics, University of Zurich, Binzmühlestrasse 14, 8050 Zurich, Switzerland. E-mail: {bouza,bernstein}@ifi.uzh.ch

Note: [] Corresponding author.

Abstract: Recommender systems play an important role in helping people finding items they like. One type of recommender system is collaborative filtering that considers feedback of like-minded people. The fundamental assumption of collaborative filtering is that people who previously shared similar preferences behave similarly later on. This paper introduces several novel, classification-based similarity metrics that are used to compare user preferences. Furthermore, the concept of partial preference similarity based on a machine learning model is presented. For evaluation the cold-start behavior of the presented classification-based similarity metrics is evaluated in a large-scale experiment. It is shown that classification-based similarity metrics with machine learning significantly outperforms other similarity approaches in different cold-start situations under different degrees of data-sparseness.

Keywords: User similarity, partial user similarity, collaborative filtering, cold-start problem

DOI: 10.3233/SW-130099

Journal: Semantic Web, vol. 5, no. 1, pp. 47-64, 2014