Numerical Similarity Measures Versus Jaccard for Collaborative Filtering

Document Type

Book Chapter

Source of Publication

Lecture Notes on Data Engineering and Communications Technologies

Publication Date

9-18-2023

Abstract

Collaborative filtering (CF) is an important method for recommendation systems, which are employed in many facets of our lives and are particularly prevalent in online-based commercial systems. The K-nearest neighbors (KNN) technique is a well-liked CF algorithm that uses similarity measurements to identify a user's closest neighbors in order to quantify the degree of dependency between the respective user and item pair. As a result, the CF approach is not only dependent on the choice of the similarity measure but also sensitive to it. However, some traditional “numerical” similarity measures, like cosine and Pearson, concentrate on the size of ratings, whereas Jaccard, one of the most frequently employed similarity measures for CF tasks, concerns the existence of ratings. Jaccard, in particular, is not a dominant measure, but it has long been demonstrated to be a key element in enhancing any measure. Therefore, this research focuses on presenting novel similarity measures by combining Jaccard with a multitude of numerical measures in our ongoing search for the most effective similarity measures for CF. Both existence and magnitude would benefit the combined measurements. Experimental results demonstrated that the combined measures are superior, surpassing all single measures across the considered assessment metrics.

ISBN

978-3-031-43246-0, 978-3-031-43247-7

ISSN

2367-4520

Publisher

Springer Nature Switzerland

Volume

184

First Page

221

Last Page

229

Disciplines

Computer Sciences

Keywords

Collaborating Filtering, Similarity Measure, Jaccard, K-Nearest Neighbor, Recommendation Systems

Indexed in Scopus

no

Open Access

no

Link to Full Text

Share

COinS