A movie Recommender System based on a hybrid intelligent optimization algorithm

Articles in Press

Document Type : Research Paper

Authors

1 Ph.D. Candidate in Information Technology Management, Department of Information Technology Management, Faculty of Management and Economics, Science and Research Branch, Islamic Azad University, Tehran, Iran

2 Assistant Professor, Department of Industrial Management, Faculty of Management and Economics, Science and Research Branch, Islamic Azad University, Tehran, Iran

3 Professor, Department of Industrial Management, Faculty of Management and Economics, Science and Research Branch Islamic Azad University, Tehran, Iran

Abstract

Watching movie is kind of entertainment in modern society and Video streaming platforms are drastically increased due to technological advancement and easy access of handheld devices in the recent years. Movie recommender systems are integrated into these platforms to help users discover suitable movies and series. In fact movie recommendation systems aim at suggesting what movie to watch without having to go through the long process of choosing from a large set of movies that is time consuming and confusing. Collaborative filtering which has excellent speed and robustness in recommendation, has been widely used in various online movie streaming platforms and it helps users to find the movies based on the movie experience of other users in efficient and effective way without wasting much time. In this paper is suggested a user-based collaborative filtering recommender system on Movielens dataset which weights of similarity function and K Nearest neighbors are adjusted with a new hybrid meta-heuristic algorithm (a combination of fuzzy Grey Wolf Optimizer algorithm, Lion Optimization algorithm, Differential Evolution algorithm and Nelder-Mead method) in the form of an optimization problem. The performance of proposed algorithm is considered in terms of MAE, Precision, Recall, F-measure and new proposed measure. The results shows that improvement in prediction accuracy and recommendation quality of recommender system.

Keywords

Main Subjects

Journal of Modeling in Engineering

Articles in Press, Accepted Manuscript
Available Online from 17 May 2026

Files

History

  • Receive Date: 27 April 2025
  • Revise Date: 07 January 2026
  • Accept Date: 18 January 2026

Share

How to cite

Statistics