Research On Recommendation Algorithm Based On Forgetting Function And Project Popularity

Due to the rapid development of Internet technology,e-commerce has gradually become an indispensable part of our lives.Many e-commerce platform for us to provide a wealth of goods,but also for consumers to provide a lot of convenient services.But how to provide consumers with more accurate recommendation is the current major e-commerce platform urgently need to solve the problem,so the study of new recommended technology or improved the previously proposed method has become a hot topic nowadays,and recommended the most critical technology Is the application of the recommended algorithm.In the present,there are many recommended algorithms,the collaborative filtering recommendation algorithm used the most.Although the collaborative filtering recommendation application is so extensive,with the increase in the number of registered users and the number of products,the accuracy and recommendation effect of the collaborative filtering algorithm is worse,and the effective solution to this problem can improve the loyalty and satisfaction of the user.Based on the above research background,this paper focuses on the problem of inaccurate calculation of the similarity of the cooperative recommendation algorithm in the proposed algorithm,and proposes an improved algorithm based on forgetting function and project popularity.The main idea is that Forgetting function and project popularity factors to improve.Based on the traditional user similarity algorithm,the similarity degree algorithm of the user is obtained by combining the above two conditions,and the products of interest are recommended for the users.Finally,with the help of the Movielens dataset,the recommended scheme proposed in this paper is tested.And compared with the traditional recommendation algorithm,the experimental results show that the proposed algorithm effectively improves the recommendation accuracy.In order to better test the recommended results of this article,this paper developed a recommended algorithm for WEB applications to better improve the user experience.