Effects of Binary Vectors Similarities on the Accuracy of Multi-Criteria Collaborative Filtering

Abstract

Recommender systems offer tailored recommendations by employing various algorithms, and collaborative filtering is one of the well-known and commonly used of those. A traditional collaborative filtering system allows users to rate on a single criterion. However, a single criterion may be insufficient to indicate preferences in domains such as restaurants, movies, or tourism. Multi-criteria collaborative filtering provides a multi-dimensional rating option. In similarity-based multi-criteria collaborative filtering schemes, existing similarity methods utilize co-users or co-items regardless of how many there are. However, a high correlation with a few co-ratings does not always provide a reliable neighborhood. Therefore, it is very common, in both single- and multi-criteria collaborative filtering, to weight similarities with functions utilizing the number of co-ratings. Since multi-criteria collaborative filtering is yet growing, it lacks a comprehensive view of the effects of similarity weighting. This work studies multi-criteria collaborative filtering and the literature of binary vector similarities, which are frequently used for weighting, by giving a related taxonomy and conducts extensive experiments to analyze the effects of weighting similarities on item- and user-based multi-criteria collaborative filtering. Experimental findings suggest that prediction accuracy of item-based multi-criteria collaborative filtering can be boosted by especially binary vector similarity measures which do not consider mutual absences.