Responsible Process Mining - A Data Quality Perspective

Modern organisations consider data to be their lifeblood. The potential benefits of data-driven analyses include a better understanding of business performance and more-informed decision making for business growth. A key road block to this vision is the lack of transparency surrounding the quality of data. A process mining study that utilises low-quality, unrepresentative data as input has little or no value for the organisation and becomes a catalyst for erroneous conclusions (‘Garbage-in-Garbage-out’). Many process mining techniques do not take into account inherent inaccuracies in the data, or how the data might have been manipulated or pre-processed. It is thus impossible to ascertain the degree to which analysis outcomes can be relied upon. This tutorial paper outlines foundational concepts of data quality with a special focus on typical data quality issues found in event data used for process mining analyses. Key challenges and possible approaches to tackle these data quality problems are elaborated on.