An entropy-based clustering ensemble method to support resource allocation in business process management

Resource allocation, as a crucial task of business process management, has been widely acknowledged by its importance for process performance improvement. Although some methods have been proposed to support resource allocation, there is little effort to allocate resources from the task preference perspective. This paper proposes a novel mechanism in which resource allocation is considered as a multi-criteria decision problem and solved by a new entropy-based clustering ensemble approach. By mining resource characteristics and task preference patterns from past process executions, the “right” resources could be recommended to improve resource utility. Further, to support dynamic resource allocation in the context of multiple process instances running concurrently, a heuristic method is devised to deal with resource conflicts caused by the interplay between various instances. The effectiveness of this study is evaluated with a real-life scenario, and the simulation results indicate that resource utility can be improved and resource workload can be balanced with the support of resource recommendation.