A MULTI OBJECTIVE OPTIMIZATION ALGORITHM FOR RECOMMENDER SYSTEM BASED ON PSO

Zhao-Xing Li^{1, 2}, Li-le He¹

¹School of Mechanical and Electrical Engineering, Xi’an University of Architecture and Technology, Xi’an 710055, China

²School of Information Engineering, Yulin University, Yulin 719000, China

In order to follow the development of Internet information service and improve the accuracy of recommender systems and recommendation algorithm. An optimal selection approach of multi-objective and particle swarm optimization (MOP-PSO) was put forward based on PSO algorithm. Furthermore, through two sets are combined and repeated dynamic adjustments, to achieve a better balance in algorithm efficiency and accuracy. Proposed a weighted cosine similarity method to calculate the user similarity, and then optimizing the weight by the PSO algorithm. Simulation results show that the algorithm has a better effective and can effectively improve the scoring accuracy, effectively improve the quality of the recommendation system.