Reputation-driven recommendation of services with uncertain QoS

Service recommendation in a Web of services with uncertain QoS is a challenging problem. In this paper, we propose a reputation-based service recommendation framework. We formally define a service reputation model that analyzes the relations between uncertain QoS and reputation. We also devise a two-phase planning approach to constructing a composite service as the recommendation when none of existing services can fulfill the user's requirements alone. Furthermore, we design a utility difference based approach that can fairly distribute the overall rating of a composite service to its component services and theoretically prove its fairness. We evaluate the efficiency and fairness of our framework on a publicly available dataset: ICEBE05.