A Survey on Concept Drift in Process Mining

Abstract

Concept drift in process mining (PM) is a challenge as classical methods assume processes are in a steady-state, i.e., events share the same process version. We conducted a systematic literature review on the intersection of these areas, and thus, we review concept drift in process mining and bring forward a taxonomy of existing techniques for drift detection and online process mining for evolving environments. Existing works depict that (i) PM still primarily focuses on offline analysis, and (ii) the assessment of concept drift techniques in processes is cumbersome due to the lack of common evaluation protocol, datasets, and metrics.

arXiv comment38 pages, ACM Computing Surveys

References in corpus (5)

• Optimal detection of changepoints with a linear computational cost
• Selective review of offline change point detection methods
• Detecting sudden and gradual drifts in business processes from execution traces
• Heuristics Miners for Streaming Event Data
• Event Stream-Based Process Discovery using Abstract Representations

Cited by in corpus (8)

• Robotic Process Automation Using Process Mining $\unicode{x2013}$ A Systematic Literature Review
• Tailoring Machine Learning for Process Mining
• Out-of-Distribution Generalization in Time Series: A Survey
• A Systematic Literature Review on Process-Aware Recommender Systems
• Interpretable Model Drift Detection
• Reinforcement Learning-supported AB Testing of Business Process Improvements: An Industry Perspective
• Resilience to the Flowing Unknown: an Open Set Recognition Framework for Data Streams
• Gradual Drift Detection in Process Models Using Conformance Metrics