Increasing the Effectiveness of Personalized Recommender Systems Based on the Integrated GNN-RL Model

Abstract

A modern approach to personalized recommendation systems is presented, combining graph neural networks GNN with RL reinforcement learning methods. The GNN model is optimized for recommendation systems and is trained on vector representations of users and products, which are used to generate an initial list of recommendations that are fed into the RL model. Particular attention is paid to the architecture and operation of the integrated GNN-RL model. The results of experimental studies demonstrating the effectiveness of the proposed approach are presented.