Personalized recommendation algorithm fusing multiple factors in edge computing
As traditional recommendation algorithms using single context information cannot effectively solve information overload,data sparsity,and cold start problems,a personalized recommendation algorithm F-SVD based on edge computing fusing multiple factors and a new user similarity calculation method F-PEARSON(improved PEARSON correlation coefficient)are proposed.Processing personalized user data at the edge server to spread the pressure of the cloud server,the current mostly centralized processing cannot provide accurate recommendations under the explosive growth of data,and fusing multiple factors at the cloud server to mine the potential relationships between users to build the predictive F-SVD algorithm.The experimental results show that on the public dataset MovieLens,compared with the traditional algorithm,the proposed algorithm has smaller errors on RMSE and MAE,and the accuracy is improved by 2.2%.
万方数据
维普
