Rating Pattern Formation for Better Recommendation

Abstract

Collaborative Filtering Recommender Systems are used to recommend items that may match each user preference on the basis of preferences of similar users in the system. Since different users have different patterns of preference, there is a problem when one user's preference is used to recommend another user's preference. A way of converting one user's preference pattern into another user's pattern is proposed. However, there are several problems with current methods: some methods take many users' patterns as a similar one, some rely on co-rated items data between user pairs which is hardly obtained, and some methods can't exactly convert a rating to a suitable one. This work proposes a new transpose function that can be utilized on any pair of users regardless of using co-rated items by applying latent model. The new transpose function is composed of an original value term and an adjustment term which transposes an original rating to an average of the target user's rating on the corresponding items. Moreover, for more accuracy, a distribution term and a confidence term are combined to the adjustment term. This new function provides better results than the current transpose function in terms of three evaluation metrics (MAE, F-measure, and coverage).