Process mining and visual analytics : breathing life into business process models

W.M.P. Aalst, van der, M. Leoni, de, A.H.M. Hofstede, ter

Research output: Book/ReportReportAcademic

6 Downloads (Pure)


Process mining and visual analytics are two disciplines that emerged over the last decade. The goal of process mining is to use event data to extract process-related information, e.g., to automatically discover a process model by observing events recorded by some information system or to check the conformance of a process model with actual process executions. The spectacular growth of event data provides unprecedented opportunities and has triggered the development of a range of process mining techniques over the last decade. Despite the wonderful capabilities of existing algorithms, it has become clear that human judgment is essential in ¿nding interesting and relevant patterns. Visual analytics combines automated analysis with interactive visualizations so as to allow decision makers to combine their ¿exibility, creativity, and background knowledge to come to an effective understanding of situations in the context of large data sets. This paper combines ideas from these two disciplines (i.e., process mining and visual analytics). In particular, we focus on replaying event logs on "maps" (i.e., visual representations of a process from a particular angle). If the visualization of a business process at a particular moment corresponds to "photo", then the (iterative) replay of an event log can be seen as a "movie". This way event logs can be used to "breathe life" into otherwise static process models. The insights obtained from such visualizations can be used to improve processes by removing inef¿ciencies and addressing non-compliance.
Original languageEnglish
PublisherBPMcenter. org
Number of pages31
Publication statusPublished - 2011

Publication series

NameBPM reports


Dive into the research topics of 'Process mining and visual analytics : breathing life into business process models'. Together they form a unique fingerprint.

Cite this