出版社:Academy & Industry Research Collaboration Center (AIRCC)
摘要:We propose an NMF (Nonnegative Matrix Factorization)-based approach in collaborativefiltering based recommendation systems to improve the Cold-Start-Users predictions sinceCold-Start-Users suffer from high error in the results. The proposed method utilizes the trustnetwork information to impute a subset of the missing ratings before NMF is applied. Weproposed three strategies to select the subset of missing ratings to impute in order to examinethe influence of the imputation with both item groups: Cold-Start-Items and Heavy-Rated-Items;and survey if the trustees' ratings could improve the results more than the other users. Weanalyze two factors that may affect results of the imputation: (1) the total number of imputedratings, and (2) the average of imputed rating values. Experiments on four different datasetsare conducted to examine the proposed approach. The results show that our approachimproves the predicted rating of the cold-start users and alleviates the impact of imputedratings.