Quality-Informed Process Mining: A Case for Standardised Data Quality Annotations

Abstract

Real-life event logs, reflecting the actual executions of complex business processes, are faced with numerous data quality issues. Extensive data sanity checks and pre-processing are usually needed before historical data can be used as input to obtain reliable data-driven insights. However, most of the existing algorithms in process mining, a field focusing on data-driven process analysis, do not take any data quality issues or the potential effects of data pre-processing into account explicitly. This can result in erroneous process mining results, leading to inaccurate or misleading conclusions about the process under investigation. To address this gap, we propose data quality annotations for event logs, which can be used by process mining algorithms to generate quality-informed insights. Using a design science approach, requirements are formulated, which are leveraged to propose data quality annotations. Moreover, we present the ‘Quality-Informed visual Miner’ plug-in to demonstrate the potential utility and impact of data quality annotations. Our experimental results, utilising both synthetic and real-life event logs, show how the use of data quality annotations by process mining techniques can assist in increasing the reliability of performance analysis results.

Foundations of Process Event Data

“…This could lead to misleading or inaccurate conclusions about the process under investigation. In [30], the authors proposed a range of quality annotations at event, trace and log levels to keep track of the data quality issues founded in an event log and also to record the extent of repairs are made to the event log as a result. Such metadata about data quality can assist in undertaking quality-informed process mining.…”

Everything there is to Know about Stochastically Known Logs

“…Existing techniques for data-driven process analysis, researched and practiced under the umbrella of process mining, are limited in their support for uncertain data. Specifically, event logs that are only stochastically known are often cleaned [4], [5] or transformed into less informative deterministically known logs by ad-hoc approaches for noise reduction, e.g., by maximum likelihood estimation or thresholding. As a consequence, data uncertainty is hidden from the actual analysis, which potentially introduces a bias and prevents any assessment of the confidence that should be put into the results and exposed to downstream applications.…”