Tuning Machine Learning to Address Process Mining Requirements

IEEE Access, vol. 12, pp. 24583–24595

Abstract

Machine learning models are routinely integrated intoprocess miningpipelines to carry out tasks like data transformation, noise reduction, anomaly detection, classification, and prediction. Often, the design of such models is based on some ad-hoc assumptions about the corresponding data distributions, which are not necessarily in accordance with thenon-parametricdistributions typically observed with process data. Moreover, the learning procedure they follow ignores the constraintsconcurrencyimposes on process data. Dataencodingis a key element to smooth the mismatch between these assumptions but its potential is poorly exploited. In this paper, we argue that a deeper understanding of the challenges associated with training machine learning models on process data is essential for establishing a robust integration of process mining and machine learning. Our analysis aims to lay the groundwork for a methodology that aligns machine learning with process mining requirements. We encourage further research in this direction to advance the field and effectively address these critical issues.

Authors 4

1. Paolo Ceravolo

   University of Milan

   Affiliation as printed

   Department of Computer Science, University of Milan, Milan, Italy

2. Sylvio Barbon

   University of Trieste

   Affiliation as printed

   Department of Engineering and Architecture, University of Trieste, Trieste, Italy

3. Ernesto Damiani

   Khalifa University of Science and Technology

   Affiliation as printed

   Department of Electrical Engineering and Computer Science, Khalifa University, Abu Dhabi, United Arab Emirates

4. Wil M. P. van der Aalst Aachen Chair of Process and Data Science

   RWTH Aachen University

   Affiliation as printed

   Chair of Process and Data Science, RWTH Aachen University, Aachen, Germany