Detecting and repairing data quality issues that affect activity labels in process event logs

Project overview

Process mining, as a well-established research area, uses algorithms for process-oriented data analysis. Similar to other types of data analysis, existence of quality issues in input data will lead to unreliable analysis results (garbage in – garbage out). An important input for process mining is an event log which is a record of events related to business process as it is performed through the use of a process-aware information system. While addressing quality issues in event logs is necessary, it is usually an ad-hoc and tiresome task. In this project, we investigate a number of approaches to detect and repair activity label quality issues that are critical for the success of process mining studies.


  • Improving the quality of real-life organisational event logs which ultimately leads to more reliable process mining outcomes.
  • Enabling contribution of public users for improving the quality of event logs.
  • Increasing domain expert engagement in providing input for improving the quality of event logs.

Project team