Application Research Of Clustering And Matrix Factorization Technology In Recommendation System

With the rapid development of Internet,the world wide web has already become the main platform for information diffusion and acquisition,and the amount of information is growing at a geometric level.Although the users can get the information in the web page very intuitively through the browser,in a short period of time,it is difficult to find information that they are interested in.Personalized recommendation system is a proposed intelligent agent system to solve the problem.That is,according to user's information,including user's nature,user's data,user's preferences,and user's purchase behavior,recommend information and items of interest to users,is a targeted recommendation.Based on clustering algorithm and matrix decomposition algorithm,this paper presents collaborative filtering recommendation for users,expressed as follows:(1)Improved personalized recommendation based on user attributes clustering and score matrix filling.In this paper,a novel evolutionary clustering method is presented.The goal of the algorithm is to gather users with similar interest into the same cluster and recommend items for users that they might like.Firstly,user attribute distance is calculated.According to the constructed network clustering model,states of users evolve over time.States of users would be stable after some period of iterations.In light of stable states of users,they are clustered into several groups.The user's interest preferences change over time,while the user's interests are relatively stable over a shorter period of time.Secondly,we fill the rating matrix based on scoring time and item genres.Thirdly,user-based collaborative filtering is adopted in each cluster.Similarities between users only in same cluster are computed with the filled matrix.Finally,the target rating is calculated according to the neighbor set of the users,and the top-N interested items are recommended to the target user.Through experiments,compared with the existing recommendation algorithms,the proposed algorithm improves the precision of recommendation and solves the sparse problem of rating matrix effectively.(2)Collaborative filtering recommendation based on filled matrix singular value decomposition and similarity weighting.This paper aims at the characteristics of the filled score matrix,decomposing the filled matrix,the user similarity matrix is calculated by decomposed matrix.Then,calculating the another user similarity matrix based on the original scoring matrix,and the two similarity matrices are weighted.Finally,select a neighbor set,based on user collaborative filtering,we predict scores and generate recommendations.Through experiments,compared with the existing recommendation algorithms,the proposed algorithm improves the precision of recommendation.