Context-Aware Based Item Recommendation for Personalized Service

Abstract

One of the personalized service in the ubiquitous environment is to provide services or items, which reflect personal tastes, attitudes, and contexts. Because the existing recommendation system performs the recommendation by using the information directly input by users and application usage record only, it is not possible to reflect the context information generated in u-healthcare environments. This study develops a item context-aware model using the context information provided by the context information model and applies it to the extraction of the missing value in a collaborative filtering process. The item context-aware model reflects the information that selects items by users according to the proper context using the C-HMM and provides it to users. In a preference based item supply method, the solution of the missing value in the preference significantly affects the recommendation accuracy. As a result, this study developed a new collaborative filtering for ubiquitous environments through reflecting the missing preference value and reflecting it to the collaborative filtering using the context-aware model.