Title: Fraud detection in process aware systems
Authors: Fabio Bezerra, Jacques Wainer
Addresses: Institute of Computing – UNICAMP, Av. Albert Einstein, 1251, Campinas, Sao Paulo, Brazil. ' Institute of Computing – UNICAMP, Av. Albert Einstein, 1251, Campinas, Sao Paulo, Brazil
Abstract: In the last years, some large companies have been involved in scandals related to financial mismanagement, which represented a large financial damage to their stockholders. To recover market confidence, certifications for best practices of governance were developed, and in some cases, harder laws were implemented. Companies adhered to these changes as a response to the market, deploying process aware systems (PAS) and adopting the best practices of governance. However, companies demand a rapid response to strategic changes or changes in business models between partners, which may impose serious drawbacks to the adoption of normative PAS to the competitiveness of these companies. Thus, while companies need flexible PAS, flexibility may compromise security. To re-balance the trade-off between security and flexibility, we present in this work an anomaly detection algorithm for PAS. The identification of anomalous events can help the adoption of flexible PAS without the loss of security properties.
Keywords: anomaly detection; process aware systems; process mining; flexible workflow systems; fraud detection; accounting scandals; mismanagement; financial damage; stockholders; market confidence; certification; best practice; corporate governance; legislation; rapid responses; strategic change; business models; partners; competitiveness; flexibility; compromises; security; trade-offs; algorithms; anomalous events; business process integration; business process management.
DOI: 10.1504/IJBPIM.2011.040204
International Journal of Business Process Integration and Management, 2011 Vol.5 No.2, pp.121 - 129
Published online: 18 Mar 2015 *
Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article