Occupational fraud detection through visualization

Occupational fraud affects many companies causing them economic loss and liability issues towards their clients and other entities. Detecting internal fraud requires significant effort since a huge amount of data produced by diverse systems (which are mostly in textual form) has to be processed with little automated support. In this paper, we exploit the advantages of information visualization and present a system that aims to detect occupational fraud in systems which involve a pair of entities (e.g., an employee and a client). The main visualization is a spiral on which the events are drawn according to their time-stamp. Suspicious events are considered those which appear along the same radius or on close radii. The system ranks both entities according to the specifications of the auditor and a video file of their activity is generated such that events with strong evidence of fraud appear first. The system is equipped with several visualizations that facilitate the detection procedure.