Performance analysis of business processes from event logs and given process models
Arya Adriansyah · TU/e Research Portal · 2009
The goal of performance analysis of business processes is to gain insights into operational processes, for the purpose of optimizing them. To intuitively show which parts of the process might be improved, performance analysis results can be projected onto process models. This way, bottlenecks can quickly be identified and resolved. Unfortunately, existing approaches to project performance information onto process models are limited to models at relatively low levels of abstraction. Given complex processes with many activities and complex case routings, useful insights are hardly obtained from classical process models. Too many details are shown at once, thus making it impossible to see the global picture. In this thesis, we investigate an approach to project performance information which is obtained from event logs onto models at any level of abstraction. Based on an analysis of existing process models, we propose a process model which can represent processes intuitively, regardless of their complexity. Given such a model and an event log of a process, we propose an approach to calculate performance information of the process. The obtained information is then projected onto the process model such that performance insights can be obtained intuitively. To evaluate the performance and demonstrate the applicability of our approach, we have implemented it in the ProM framework and tested it using various real-life event logs.