A Proactive Multi-type Context-Aware Recommender System in the Environment of Internet of Things

Abstract

Currently recommender systems are incorporating context and social information of the user, producing context aware recommender systems. In the future, they will use implicit, local and personal information of the user from the Internet of Things, where anyone and anything will be connected at anytime and anywhere. Most recommender systems follow a request-response approach in which the recommendations are provided to the user upon his request. Recently a proactive recommender system - that pushes recommendations to the user when the current situation seems appropriate, without explicit user request - has been introduced in the research area of recommender systems. The fact that the future is for Internet of Things, and the emergence of proactivity concept leads to our system design, in which multi-type rather than one type of recommendations will be recommended proactively to the user in real time. In this paper, a design of a context aware recommender system that recommends different types of items proactively under the Internet of Things paradigm is proposed. A major part of this design is the context aware management system. In this system, we have used a neural network that will do the reasoning of the context to determine whether to push a recommendation or not and what type of items to recommend. The neural network inputs are derived virtually from the Internet of Things, and its outputs are scores for three types of recommendations, they are: gas stations, restaurants and attractions. These scores have been used to decide whether to push a recommendation or not, and what type of recommendations to push among these three types. The results of 5000 random contexts were tested. For an average of 98% of them, our trained neural network generated correct recommendation types in the correct times and contexts.