FCNHSMRA_HRS: Improve the performance of the movie hybrid recommender system using resource allocation approach

TL;DR

This paper introduces FCNHSMRA_HRS, a hybrid movie recommender system that combines fuzzy clustering, heuristic similarity, and resource allocation to enhance accuracy, scalability, and performance, especially with limited rating data.

Contribution

It proposes a novel hybrid approach integrating fuzzy clustering and resource allocation to improve movie recommendation accuracy and scalability over traditional collaborative filtering methods.

Findings

Improved accuracy and precision over existing methods.

Enhanced scalability with fuzzy clustering.

Better performance metrics on MovieLens dataset.

Abstract

Recommender systems are systems that are capable of offering the most suitable services and products to users. Through specific methods and techniques, the recommender systems try to identify the most appropriate items, such as types of information and goods and propose the closest to the user's tastes. Collaborative filtering offering active user suggestions based on the rating of a set of users is one of the simplest and most comprehensible and successful models for finding people in the same tastes in the recommender systems. In this model, with increasing number of users and movie, the system is subject to scalability. On the other hand, it is important to improve the performance of the system when there is little information available on the ratings. In this paper, a movie hybrid recommender system based on FNHSM_HRS structure using resource allocation approach called FCNHSMRA_HRS is presented. The FNHSM_HRS structure was based on the heuristic similarity measure (NHSM), along with fuzzy clustering. Using the fuzzy clustering method in the proposed system improves the scalability problem and increases the accuracy of system suggestions. The proposed systems is based on collaborative filtering and, by using the heuristic similarity measure and applying the resource allocation approach, improves the performance, accuracy and precision of the system. The experimental results using MAE, Accuracy, Precision and Recall metrics based on MovieLens dataset show that the performance of the system is improved and the accuracy of recommendations in comparison of FNHSM_HRS and collaborative filtering methods that use other similarity measures for finding similarity, is increased