Home // International Journal On Advances in Intelligent Systems, volume 8, numbers 3 and 4, 2015 // View article

Service Recommendation Using Machine Learning Methods Based on Measured Consumer Experiences Within a Service Market

Authors:
Jens Kirchner
Andreas Heberle
Welf Löwe

Keywords: Service Selection; Service Recommendation; Machine Learning; Non-functional properties; Performance gain.

Abstract:
Among functionally similar services, service consumers are interested in the consumption of the service that performs best towards their optimization preferences. The experienced performance of a service at consumer side is expressed in its non-functional properties. Selecting the best-fit service is an individual aspect as the preferences of consumers vary. Furthermore, service markets such as the Internet are characterized by perpetual change and complexity. The complex collaboration of system environments and networks result in various performance experiences at consumer side. Service optimization based on a collaborative knowledge base of previous experiences of other, similar consumers with similar preferences is a desirable foundation. In this article, we present a service recommendation framework, which aims at the optimization at consumer side focusing on the individual preferences and call contexts. In order to identify relevant non-functional properties for service selection, we conducted a literature study of conference papers of the last decade. The ranked results of this study represent what a broad scientific community determined to be relevant non-functional properties for service selection. We furthermore analyzed, implemented, and validated machine learning methods that can be employed for service recommendation. Within our validation, we could achieve up to 95% of the overall achievable performance (utility) gain with a machine learning method that is focused on concept drift, which in turn, tackles the change characteristic of the Internet being a service market. Besides the comprehensive and scientific identification of relevant non-functional properties when selecting a service, this article describes how machine learning can be employed for service recommendation based on consumer experiences in general, including an evaluation and overall proof of concept validation within our framework.

Pages: 347 to 373

Copyright: Copyright (c) to authors, 2015. Used with permission.

Publication date: December 30, 2015

Published in: journal

ISSN: 1942-2679