Uncovering the Relationship Between Event Log Characteristics and Process Discovery Techniques

Abstract

The research eld of process mining deals with the extraction of knowledge from event logs. Event logs consist of the recording of activities that took place in a certain business environment and as such, one of process mining's main goals is to get an insight on the execution of business processes. Although a substantial eort has been put on developing techniques which are able to mine event logs accurately, it is still unclear how exactly characteristics of the latter inuence a technique's performance. In this paper, we provide a robust methodology of analysis and subsequently derive useful insights on the role of event log characteristics in process discovery tasks by means of an exhaustive comparative study.

A comparative study of existing quality measures for process discovery

“…Therefore, no conclusions on the relationship between metrics within and among dimensions were drawn. Finally, in vanden Broucke et al [30], metrics were compared within dimensions. Here, the hypothesis that the average of different metrics within each dimension were equal was rejected.…”