Design of a Recommendation System for an Efficient and Optimized (RSU) Usage and Protect from External Influences

In recent years, recommendation systems have become prevalent in various domains, such as multimedia streaming, e-commerce and social media, enhancing user experience through personalized content delivery. However, these systems are vulnerable to external influences that can distort recommendations and lead to biased results. This paper presents a novel recommendation system that optimizes the usage of Resource Sharing Units (RSUs) while protecting against external manipulation. The proposed model benefits both content providers and users by delivering accurate, preference-aligned recommendations without succumbing to external bias, thanks to advanced filtering mechanisms that detect and block potential interference. Furthermore, the system is optimized for efficient memory utilization, reducing computational load and enhancing performance. Extensive testing demonstrates its ability to resist external manipulation while maintaining optimal RSU usage offering a robust solution for personalized content delivery in manipulation-prone environments.