Department of Labor Office of Inspector General wanted to detect fraud in Office of Workers’ Compensation Program data. The project goals were to highlight abnormalities in the claims data that could be used for future audits and to create visualization tools to allow auditors to easily explore potentially fraudulent claims.
Elder Research developed a predictive fraud solution and data visualization tool for the Office of Audit staff based on the attributes of known fraud cases from the Office of Labor Racketeering and Fraud Investigations case management database comprised of over 900,000 cases and their supporting case management, bill pay, compensation, and chargeback data from the four previous fiscal years. Three databases were joined together at the case level allowing disparate data sources to be displayed together in a meaningful way. The fraud results and supporting data are viewable in an easy-to-use visualization tool called RADR (Risk Assessment Data Repository). The tool enables auditors to access and visualize data on high-risk claims. Auditors can view claim risk scores in either a list view (shown below) or a map view.
The production ensemble model generated a fraud risk score for each of nearly one million cases. Our team was able to determine that analyzing the top 21% of the cases with the highest risk scores would enable auditors to identify 90% of actual fraud cases. The interactive visualization provided by RADR allows the client to rank cases by risk, to filter cases by dollar value or other attributes, and to drill down into cases to quickly determine if they are worth pursuing. Research that would have taken days is now done in hours, greatly improving auditor productivity. The RADR fraud solution is being used by more than 150 DOL-OIG investigators and auditors across the country.