A Trust Assisted Matrix Factorization based Improved Product Recommender System

Abstract

Smart services is an efficient concept to provide services to the citizen in an efficient manner. The online shopping and recommender system play an important role in this scenario that provides efficient item recommendations to the citizens. Though, the majority of the latest recommender systems can't get effective and efficient prediction accuracy because of the sparsity of the item matrix against each user. Additionally, the recommendations are not reliable when tested upon larger datasets. To handle these problems, a trust-based technique is proposed, called trustasvd++, which fuses a user's trust data in the MF con. The offered strategy combines trust data and rating values to deal with the sparsity and cold start user's issues. Matrix Factorization (MF) has been recognized as a persuasive method for the formation of an effective Recommender System. Pearson correlation coefficient (PCC) is used as a similarity metric in the proposed technique. To assess the efficiency of the offered strategy, numerous datasets have been done on datasets including Epinions, Filmtrust, and Ciao.