The actual experience of the performance of services at consumers’ side is a desirable foundation for service selection. Considering the knowledge of previous performance experiences from a consumer’s perspective, a service broker can automatically select the best-fitting service out of a set of functionally similar services. In this paper, we present the evaluation of machine learning methods and frameworks which can be employed for service recommendation based on shared experiences of previous consumers. Implemented in a prototype, our approach considers a consumer’s call context as well as its selection preferences (expressed in utility functions). The implementation of the framework aims at the time-critical optimisation of service consumption with focus on runtime aspects and scalability. Therefore, we evaluated and employed high-performance, online and large scale machine learning methods and frameworks. Considering the Internet as a service market with perpetual change, strategies for concept drift have to be found. The evaluation showed that with the current approach, the framework recommended the actual best-fit service instance in 70% of the validation cases, while in 90% of the cases, the best or second best-fit was recommended. Furthermore, within our approach employing the best method, we achieved 94.5% of the overall maximum achievable utility value.