Matching Business Process Behavior with Encoding Techniques via Meta-Learning: An anomaly detection study

Gabriel Marques Tavares1 and Sylvio Barbon Junior2

  1. Università degli Studi di Milano (UNIMI), Milan, Italy
    gabriel.tavares@unimi.it
  2. Università degli Studi di Trieste (UniTS), Trieste, Italy
    sylvio.barbonjunior@dia.units.it

Abstract

Recording anomalous traces in business processes diminishes an event log’s quality. The abnormalities may represent bad execution, security issues, or deviant behavior. Focusing on mitigating this phenomenon, organizations spend efforts to detect anomalous traces in their business processes to save resources and improve process execution. However, in many real-world environments, reference models are unavailable, requiring expert assistance and increasing costs. The considerable number of techniques and reduced availability of experts pose an addi-tional challenge for particular scenarios. In this work, we combine the representational power of encoding with a Meta-learning strategy to enhance the detection of anomalous traces in event logs towards fitting the best discriminative capability between common and irregular traces. Our approach creates an event log profile and recommends the most suitable encoding technique to increase the anomaly detection performance. We used eight encoding techniques from different families, 80 log descriptors, 168 event logs, and six anomaly types for experiments. Results indicate that event log characteristics influence the representational capability of encodings. Moreover, we investigate the process behavior’s influence for choosing the suitable encoding technique, demonstrating that traditional process mining analysis can be leveraged when matched with intelligent decision support approaches.

Key words

Anomaly detection, Meta-learning, Encoding, Process mining, Recommendation

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS220110005T

Publication information

Volume 20, Issue 3 (June 2023)
Year of Publication: 2023
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Tavares, G. M., Junior, S. B.: Matching Business Process Behavior with Encoding Techniques via Meta-Learning: An anomaly detection study. Computer Science and Information Systems, Vol. 20, No. 3, 1207–1233. (2023), https://doi.org/10.2298/CSIS220110005T