Smart Prediction Assistant: An Innovative Customer Intelligence Platform For Next Generation Ambient Recommender Systems

The objective of this paper is twofold: first, to introduce Smart User Models (SUM) to improve file personalization in next generation Ambient Recommender Systems; and second, the application of SUM through a Smart Prediction Assistant (SPA) platform in an Intelligent Learning Guide with more than three million users. SUM acts oil behalf of users by learning from their interactions while reducing information overload through highly relevant recommendations ill everyday life. In particular, SUM can enrich users' preferences and interests according to their emotional sensitivity. This paper provides a cross-disciplinary perspective to achieve this goal in such a recommender system through a SPA platform. While most approaches to recommending have focused on algorithm performance, SPA makes recommendations to users oil the basis of emotional information acquired in an incremental way. The methodology applied in SPA is the result of a technology transfer project for real-world recommender systems.