Incorporating User Item Similarity in Hybrid Neighborhood-Based Recommendation Systems

Abstract

Recommendation systems have been developed in many domains to help users with information overload from the large volume of online multimedia content by providing them with appropriate options. Recently developed hybrid recommendation systems require a large amount of data to understand users’ interests and give appropriate suggestions. However, several internet privacy issues make users skeptical about sharing their personal information with online service providers, limiting the potential of these systems. The study in this paper introduces various novel methods utilizing the baseline estimate to learn user interests in specific item features from their past interactions. Subsequently, extracted user feature vectors are implemented to estimate the user-item correlations, providing an additional fine-tuning factor for neighborhood-based collaborative filtering systems. Comprehensive experiments show that utilizing the user-item similarity scores in the rating prediction task can improve the accuracy of hybrid neighborhood-based systems by at least 2.11% compared to traditional methods while minimizing the need for tracking users' digital footprints.