A Survey on Swarm Intelligence Algorithms Employed for Optimizing Machine Learning Techniques Used in Recommendation Systems

With the exponential growth of digital data, recommendation systems or recommender systems are widely used in various domains assisting users in filtering and decision-making on massive information. Recommendation systems are capable of delivering personalized content to enhance user experience and satisfaction through users' preferences and behaviors. The machine learning algorithms employed in the recommendation systems facilitate the effectiveness of tasks achieved by those systems among which, for example, is providing accurate prediction that matches user preferences. Swarm Intelligence offers robust optimization mechanisms that have been successfully applied in various computational problems including recommendation systems for refining recommendation algorithms. To the best of our knowledge, there is no recent comprehensive survey on swarm intelligence algorithms used for optimizing machine learning techniques when used in recommendation systems. Therefore, this survey presents a survey of the swarm intelligence algorithms used in optimizing the machine learning techniques when employed in recommendation systems. We conducted a literature survey on recommendation systems and swarm intelligence, using relevant keywords and their variants, focusing on recent publications since 2019. Our findings highlight the use of swarm intelligence algorithms primarily in clustering, classification, and feature selection for recommendation systems. Swarm intelligence has significantly enhanced recommendation systems, especially in clustering and classification. However, the balance between computational complexity and processing speed remains a challenge. Future research could focus on refining these algorithms for better efficiency and effectiveness in recommendation systems.