The periodic product recommendation system based on deep reinforcement learning and the multi-objective framework

The primary objective of the recommendation system is to suggest suitable products to users. The need for a personalized recommendation system has become essential with the continuous growth in the number of users and the increasing diversity of products. In this paper, we proposed a novel approach that combines a reinforcement learning algorithm with user clustering to address the recommendation challenge for periodic products. Additionally, we extend our framework to accommodate multi-objective scenarios. Our contributions encompass the development of meaningful representation vectors for actions and states, along with the definition of reward vector aligning with users’ long-term preferences and optimizing profits. We apply our proposed method to the problem of recommending mobile packages in Vietnam. Notably, our approach yields favorable recommendation results and exhibits superior performance compared to alternative methods.