User-centric cloud intermediation services

Abstract

Given the wide adoption of cloud computing technology and the growing number of service providers, consumers will increasingly face the challenge of finding appropriate providers that can satisfy their functional and non-functional requirements. In this paper, we examine the exploitation of machine learning techniques in user modelling technology for cloud services as a way to inform service providers on how to target service configurations at specific market segments, as well as to advice consumers on their service requests. More specifically, we examine the organisation of consumers into meaningful subsets (communities) and the extraction of meaningful service configurations for each subset (stereotypes).