A recommendation of pension service based on user preferences and trust relationships

Recommendation technology have been widely used in social networks and many e-commerce websites, but there are few recommendations of pension service and those recommendation results are not accurate enough. For more accurately recommending personalized pension services to users, this paper proposes a recommendation method of pension service based on the user preferences and the trust relationships between users. Firstly, by mining user socialization relationship information, the degree of trust relationships between users is calculated, and the Pearson correlation coefficient is used to obtain the user similarity, then their results are combined and used to find the neighbour user set of the target user. Secondly, a timeliness model of user ratings based on the user evaluation time are established, which is used to determine the user's preference for the service, and finally to predict the target user's rating value for the project. The experiment takes the Douban review data and the users social data as the case to verify the results. The experimental results show that compared with the traditional recommendation method, the recommendation method based on user preferences and trust relationships improves the accuracy of recommendation.