Context-Aware Mobile Proactive Recommendation

Abstract

Mobile recommender systems aim to recommending the right product or information to the right users at anytime and anywhere. It is well known that the contextual information is often the key for the performances of mobile recommendations. Therefore, in this paper, we firstly identify which types of contextual information could affect users' personal preferences, which is called users' adaptive options preferences, and qualitatively construct an adaptive options analytical hierarchy process model for users' personal preferences , and quantitatively analyze impact weights of contextual information on users' personal preferences. Then we propose a novel contextaware learning algorithm for mobile users' adaptive options preferences. Secondly we divide all users into two groups according to their frequency in using of all services in history logs, and propose two different proactive recommendation methods for the two classes of users. Finally experiments are conducted to demonstrate the performance of the preference learning algorithm, the impact of contexts and the proportion of the training dataset on the algorithm, and recommendation precision of the two methods.