On the Use of Benford's Law to Detect Anomalies and Fraud in Public Health Care Contract Data

• In Event: Research in Banking and Auditing

Abstract

In this paper we propose a data analysis focused audit system where we identify and eliminate clusters of data points that do not have the characteristics of a Benford conforming data set. By looking at the attributes of these data sets, we identify potential audit candidates. We analyze a real data set using the proposed system and identify anomalies and possible fraudulent activities. We believe this systemic approach is better than a random selection process.

Authors

• Donald Kent, SUNY-Brockport

• Mustafa Canbolat, The College at Brockport (SUNY)