Enhancing Event Log Quality : Detecting and Quantifying Timestamp Imperfections

Title data

Fischer, Dominik Andreas ; Goel, Kanika ; Andrews, Robert ; van Dun, Christopher ; Wynn, Moe T. ; Röglinger, Maximilian:
Enhancing Event Log Quality : Detecting and Quantifying Timestamp Imperfections.
In: Proceedings of the 18th International Conference on Business Process Management (BPM). - Seville, Spain , 2020

Project information

Abstract in another language

Timestamp information recorded in event logs plays a crucial role in uncovering meaningful insights into business process performance and behaviour via Process Mining techniques. Inaccurate or incomplete timestamps may cause activities in a business process to be ordered incorrectly, leading to unrepresentative process models and incorrect process performance analysis results. Thus, the quality of all timestamps in an event log should be evaluated thoroughly before the event log is used as input for any Process Mining activity. To the best of our knowledge, research that focuses on the (automated) quality assessment of event logs remains scarce. Our work presents an automated approach for detecting and quantifying timestamp-related issues (timestamp imperfections) in an event log. We propose to assess the quality of timestamps in an event log across two axes: four levels of abstraction (event, activity, trace, log) and four quality dimensions (accuracy, completeness, consistency, uniqueness). In total, we define 15 timestamp quality-related metrics and demonstrate how they can be computed to assess event log quality. The approach has been implemented as a prototype within the open-source Process Mining framework, ProM, and evaluated using three real-life event logs. This approach paves the way for a systematic and interactive enhancement of timestamp imperfections during the data pre-processing phase of Process Mining projects.