No abstract

No abstract

In recent years, organizations are putting an increasing emphasis on anomaly detection. Anomalies in business processes can be an indicator of system faults, inefficiencies, or even fraudulent activities. In this paper we introduce an approach for anomaly detection. Our approach considers different perspectives of a business process such as control flow, data and privacy aspects simultaneously.Therefore, it is able to detect complex anomalies in business processes like spurious data processing and misusage of authorizations. The approach has been implemented in the open source ProM framework and its applicability was evaluated through a real-life dataset from a financial organization. The experiment implies that in addition to detecting anomalies of each aspect, our approach can detect more complex anomalies which relate to multiple perspectives of a business process.