Variational Autoencoder for Anomaly Detection in Event Data in Online Process Mining

Philippe Krajsic, Bogdan Franczyk, Bogdan Franczyk

Abstract

The analysis of event data recorded by information systems is becoming increasingly relevant. An increasing data-centric analysis of processes by using process mining techniques has a direct impact on the management of business processes. To achieve a positive impact on business process management, a high quality data basis is important. This paper presents an approach for the application of variational autoencoder for the filtering of anomalous event data in an online process mining environment, which help to improve the results of process mining techniques and thus positively influence business process management. For anomaly detection in an unsupervised environment, mass-volume and excess-mass scores are used as metrics. The results are compared on the basis of established algorithms such as one-class support vector machine, isolation forest and local outlier factor. These insights are used to highlight the benefits of this approach for process mining and business process management.

Download


Paper Citation


in Harvard Style

Krajsic P. and Franczyk B. (2021). Variational Autoencoder for Anomaly Detection in Event Data in Online Process Mining. In Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-509-8, pages 567-574. DOI: 10.5220/0010375905670574


in Bibtex Style

@conference{iceis21,
author={Philippe Krajsic and Bogdan Franczyk},
title={Variational Autoencoder for Anomaly Detection in Event Data in Online Process Mining},
booktitle={Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2021},
pages={567-574},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010375905670574},
isbn={978-989-758-509-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - Variational Autoencoder for Anomaly Detection in Event Data in Online Process Mining
SN - 978-989-758-509-8
AU - Krajsic P.
AU - Franczyk B.
PY - 2021
SP - 567
EP - 574
DO - 10.5220/0010375905670574