Applying deep learning to detect abnormal event log traces: a non-rule-based framework

Authors

• Yunsen Wang, Montclair State UniversityFollow
• Tiffany Chiu, SUNY New Paltz
• Miklos A. Vasarhelyi, Rutgers University–New Brunswick

Document Type

Article

Publication Date

11-1-2024

Journal / Book Title

International Journal of Digital Accounting Research

Abstract

Process mining is an efficient method that can analyze the full population of transactions using the event log of business processes. Conventional rule-based process mining techniques can detect anomalies; however, it tends to trigger a large number of false alarms. To improve the efficiency of anomaly detection using process mining, this study adopts a deep learning-based classification approach to detect anomalies in the traces of event logs. This approach contributes to the literature by proposing a non-rule-based process mining technique based on deep learning. Results demonstrate that the proposed non-rule-based process mining method can help auditors focus on transactional anomalies.

DOI

10.4192/1577-8517-v24_5

MSU Digital Commons Citation

Wang, Yunsen; Chiu, Tiffany; and Vasarhelyi, Miklos A., "Applying deep learning to detect abnormal event log traces: a non-rule-based framework" (2024). Department of Accounting and Finance Faculty Scholarship and Creative Works. 156.
https://digitalcommons.montclair.edu/acctg-finance-facpubs/156

Rights

This article is Open Access and distributed under a Creative Commons 4.0 license.

Published Citation

Wang, Y., Chiu, T., & Vasarhelyi, M. A. (2024). Applying deep learning to detect abnormal event log traces: a non-rule-based framework. International Journal of Digital Accounting Research, 24.