Collaborative filtering based web service recommender system using users' satisfaction on QoS attributes

Abstract

To select the best service meeting their requirements, service users prefer to personalize their non-functional attributes, such as reliability and price. But, that creates challenges as service providers have to consider contradictory non-functional attributes in the service selection process for service users. Present memory-based collaborative filtering (CF) service recommendation methods employs this recommendation technique using non-functional attribute values obtained at service invocation in order to calculate the similarity between users or items, and also to predict missing non-functional attributes. However, this approach is not sufficient as the non-functional attribute values of invoked services may not necessarily satisfy their individual preferences. In this paper, a CF-based service recommendation method using users' individual preference on non-functional attributes is proposed.