Checking Wrong Decision and Wrong Pattern by Using A Graph-based Method

Abstract

Companies in the world have been considered fraud as a crucial problem. The fraud can be caused by many things, including data manipulation and anomalies in business processes or standard operational procedures (SOP). Anomalies have several types; two of them are a wrong decision and a wrong pattern. A wrong decision, which is not in accordance with the standard list in SOP, occurs as a result of making wrong decisions. On the other hand, the wrong sequence of activities is called a wrong pattern. For detecting those two anomalies, this paper proposed a graph-based method. The graph-based method creates rules for detecting a wrong pattern by measuring the similarity between traces of SOP and the process and checks the attributes of activities to detect a wrong decision. The evaluation uses an event log of the credit application process in a bank. Based on the evaluation, the proposed graph-based method gains 100% for the accuracy value in checking wrong pattern and wrong decision.