TU Darmstadt / ULB / TUbiblio

Unsupervised Anomaly Detection in Noisy Business Process Event Logs Using Denoising Autoencoders

Nolle, Timo and Seeliger, Alexander and Mühlhäuser, Max
Calders, Toon and Ceci, Michelangelo and Malerba, Donato (eds.) (2016):
Unsupervised Anomaly Detection in Noisy Business Process Event Logs Using Denoising Autoencoders.
In: Discovery Science: 19th International Conference, DS 2016, Bari, Italy, Proceedings, Calders, Toon Ceci, Michelangelo Malerba, Donato, Bari, Italy, ISBN 978-3-319-46307-0,
DOI: 10.1007/978-3-319-46307-0_28, [Conference or Workshop Item]

Abstract

Business processes are prone to subtle changes over time, as unwanted behavior slowly manifests in the execution flow. This problem is related to anomaly detection, as these subtle changes start of as anomalies at first, and thus it is important to detect them early. However, the necessary process documentation is often outdated, and thus not usable. Moreover, the only way of analyzing a process in execution is the use of event logs coming from process-aware information systems, but these event logs already contain anomalous behavior and other sorts of noise. Classic process anomaly detection algorithms require a dataset that is free of anomalies; thus, they are unable to process the noisy event logs. Within this paper we propose a system, relying on neural network technology, that is able to deal with the noise in the event log and learn a representation of the underlying model, and thus detect anomalous behavior based on this representation. We evaluate our approach on five different event logs, coming from process models with different complexities, and demonstrate that our approach yields remarkable results of 97.2 percent F1-score in detecting anomalous traces in the event log, and 95.6 percent accuracy in detecting the respective anomalous activities within the traces.

Item Type: Conference or Workshop Item
Erschienen: 2016
Editors: Calders, Toon and Ceci, Michelangelo and Malerba, Donato
Creators: Nolle, Timo and Seeliger, Alexander and Mühlhäuser, Max
Title: Unsupervised Anomaly Detection in Noisy Business Process Event Logs Using Denoising Autoencoders
Language: German
Abstract:

Business processes are prone to subtle changes over time, as unwanted behavior slowly manifests in the execution flow. This problem is related to anomaly detection, as these subtle changes start of as anomalies at first, and thus it is important to detect them early. However, the necessary process documentation is often outdated, and thus not usable. Moreover, the only way of analyzing a process in execution is the use of event logs coming from process-aware information systems, but these event logs already contain anomalous behavior and other sorts of noise. Classic process anomaly detection algorithms require a dataset that is free of anomalies; thus, they are unable to process the noisy event logs. Within this paper we propose a system, relying on neural network technology, that is able to deal with the noise in the event log and learn a representation of the underlying model, and thus detect anomalous behavior based on this representation. We evaluate our approach on five different event logs, coming from process models with different complexities, and demonstrate that our approach yields remarkable results of 97.2 percent F1-score in detecting anomalous traces in the event log, and 95.6 percent accuracy in detecting the respective anomalous activities within the traces.

Title of Book: Discovery Science: 19th International Conference, DS 2016, Bari, Italy, Proceedings
Publisher: Calders, Toon Ceci, Michelangelo Malerba, Donato
ISBN: 978-3-319-46307-0
Divisions: 20 Department of Computer Science > Telecooperation
LOEWE > LOEWE-Schwerpunkte > NiCER – Networked infrastructureless Cooperation for Emergency Response
LOEWE > LOEWE-Schwerpunkte
20 Department of Computer Science
LOEWE
Event Location: Bari, Italy
Date Deposited: 31 Dec 2016 12:59
DOI: 10.1007/978-3-319-46307-0_28
Identification Number: TUD-CS-2016-0168
Export:

Optionen (nur für Redakteure)

View Item View Item