A Situation-Aware Proactive Recommender System

The proactive recommender system automatically delivers (i.e. pushes) recommendations to the user, without explicit request from him. The push model seems to be very effective in the applications where the availability of items changes often and rapidly, as it helps users timely receive their interested information. However, if the system pushes uninterested information to the user, or even pushes interested information to the user but at inappropriate context, then the user´s acceptance of proactively delivered recommendations will decrease enormously. Hence for improving user´s acceptance in proactive recommender systems, determination of right context (situation assessment) and finding relevant items for the target user are very crucial. This paper presents a Situation-Aw are Proactive Recommender System (SAPRS) that pushes relevant items to the target user at the right context only. The recommendation process in the proposed system is divided into two phases: (i) situation assessment phase and the (ii) item assessment phase. In situation assessment phase, the SAPRS system analyzes the current situation i.e. whether or not the current context needs a recommendation. In item assessment phase, the suitable items are selected as recommendations using a collaborative filtering approach. SAPRS uses fuzzy logic as an inference technique to handle uncertainty within situation assessment phase. The prototype of SAPRS has been designed and developed for restaurant recommendations. Performance of the implemented prototype system is evaluated using users´ subjective feedback.