Leveraging Modified Social Group Optimization for Enhanced E-Commerce Recommendation Systems

Abstract

Intelligent recommendation systems have gained significant popularity in recent times due to their ability to ease item or service selection for users and enhance profit-making opportunities for businesses. E-commerce recommender systems are in high demand across online platforms. There is a pressing need for continuous innovation to improve the performance of these e-commerce recommendation systems in terms of accuracy in suggesting preferences. However, many existing recommendation systems are not able to perform well when there is a data sparsity or incomplete data. To address above challenges, this study introduces a novel approach that combines collaborative filtering with Modified Social Group Optimization (MSGO), a type of evolutionary optimization methods. The main objective is to improve the precision of the recommendation system specifically for movie recommendations. The collaborative filtering technique is leveraged to analyse user-item interactions and find patterns to predict user preferences. To evaluate the proposed system, a simulation is conducted using movie recommendation data. The results demonstrate that the integration of MSGO into the collaborative filtering framework yields improved performance compared to the original SGO algorithm. These findings provide promising evidence for the effectiveness of MSGO in enhancing the accuracy of movie recommendations within the ecommerce context.