A Framework for Explainable Concept Drift Detection in Process Mining

TL;DR

This paper introduces a framework that enhances process mining by providing explainable detection of concept drift and identifying potential cause-effect relationships behind process changes.

Contribution

It presents a novel framework that adds explainability to concept drift detection in process mining, including causality analysis between different process perspectives.

Findings

Framework effectively uncovers cause-effect relationships

Evaluations on synthetic and real data demonstrate its usefulness

Provides new insights into process changes and their root causes

Abstract

Rapidly changing business environments expose companies to high levels of uncertainty. This uncertainty manifests itself in significant changes that tend to occur over the lifetime of a process and possibly affect its performance. It is important to understand the root causes of such changes since this allows us to react to change or anticipate future changes. Research in process mining has so far only focused on detecting, locating and characterizing significant changes in a process and not on finding root causes of such changes. In this paper, we aim to close this gap. We propose a framework that adds an explainability level onto concept drift detection in process mining and provides insights into the cause-effect relationships behind significant changes. We define different perspectives of a process, detect concept drifts in these perspectives and plug the perspectives into a causality check that determines whether these concept drifts can be causal to each other. We showcase the effectiveness of our framework by evaluating it on both synthetic and real event data. Our experiments show that our approach unravels cause-effect relationships and provides novel insights into executed processes.