Bridging abstraction layers in process mining: Event to activity mapping

Abstract

While the maturity of process mining algorithms emerges and more process mining tools enter the market, process mining projects still face the problem of different levels of abstraction when comparing events recorded by supporting IT systems with defined business activities. Current approaches for event log abstraction most often try to abstract from the events in an automated way which does not capture the required domain knowledge to fit business activities. This can lead to misinterpretation of discovered process models and wrong conformance results. We developed an approach which aims to abstract an event log to the same abstraction level which is needed by the business. Therefore, we capture domain knowledge about event to activity mappings in a formalized way and propose an algorithm to correctly cluster events to activity instances. We evaluated our approach in a case study with a German IT outsourcing company. © 2013 Springer-Verlag.