Anomaly Detection Using Process Mining
Recently, several large companies have been involved in financial scandals related to mismanagement, resulting in financial damages for their stockholders. In response, certifications and manuals for best practices of governance were developed, and in some cases, tougher federal laws were implemented (e.g. the Sarboness Oxley Act). Companies adhered to these changes adopting the best practices for corporate governance by deploying Process Aware Information Systems (PAISs) to automate their business processes. However, these companies demand a rapid response to strategic changes, so the adoption of normative PAISs may compromise their competitiveness. On one hand companies need flexible PAISs for competitiveness reasons. On the other hand flexibility may compromise security of system because users can execute tasks that could result into violation of financial loses. In order to re-balance this trade-off, we present in this work how ProM tools can support anomaly detection in logs of PAIS. Besides, we present the results of the application of our approach with a real case.
KeywordsProcess mining anomaly detection auditing systems
Unable to display preview. Download preview PDF.
- 5.Bezerra, F., Wainer, J.: Towards detecting fraudulent executions in business process aware systems. In: WfPM 2007 - Workshop on Workflows and Process Management, Timisoara, Romania (September 2007); In conjunction with SYNASC 2007Google Scholar
- 7.Bezerra, F., Wainer, J.: Anomaly detection algorithms in business process logs. In: ICEIS 2008: Proceedings of the Tenth International Conference on Enterprise Information Systems, Barcelona, Spain, June 2008. AIDSS, pp. 11–18 (2008)Google Scholar
- 12.Agrawal, R., Gunopulos, D., Leymann, F.: Mining process models from workflow logs. In: Schek, H.-J., Saltor, F., Ramos, I., Alonso, G. (eds.) EDBT 1998. LNCS, vol. 1377, pp. 469–483. Springer, Heidelberg (1998)Google Scholar