Multi-dimensional requirements for reinforcement recommendation reasoning

Abstract

Personalized recommendation systems not only need to improve the accuracy of recommendations, but also need to focus on the variety and novelty of recommendations to improve user satisfaction. Currently, most of the existing recommendation systems focus on improving the accuracy and diversity of recommendation items, however, they usually do not consider the original user needs, and the potential relationship between diversity and novelty is not deeply explored. In addition to accuracy and diversity, we also consider novelty, and analyze the relationship between diversity and novelty (same place and different place), and propose an explainable recommendation system that integrates multiple (multidimensional) requirements such as accuracy, diversity, and novelty. The model combines semantic relations of knowledge graphs and multi-hop inference so as to analyze and consider the diversity and novelty requirements of users. Meanwhile, a recurrent neural network is used to construct a temporal multi-label classification network to predict users’ multidimensional demands and capture the dependencies between diversity and novelty demands. Finally, a composite reward function, including accuracy reward, diversity reward and novelty reward, is designed to implement a multi-demand, multi-decision recommendation method. Experiments are conducted on three real-world datasets, and the experimental results show that the model can guarantee the accuracy while improving the diversity and novelty of recommended items.