Not only does Elder Research provide the data science on our projects, we also prepare the data, and deliver the results. Elder Research created RADR to visually present results, allowing our clients to easily view, explore, and act on project insights.
RADR is a powerful, server-based, data analytics product fusing data from multiple sources, supporting sophisticated predictive and machine learning risk models, and providing a flexible and intuitive visual interface.
RADR enables proactive identification of risk, fraud, waste, and abuse (RFWA) behaviors and simplifies the investigative process. RADR provides visualizations for risk propensity scores and their related data so that managers, auditors, investigators, and analysts can easily access data on high-risk items and focus on the highest ROI cases.
The foundation for RADR is an open source visualization and workflow system called Metabase. Building on this foundation, Elder Research creates additional capabilities tailored to client needs, making RADR the most intuitive RFWA tool in the industry.
- Contract Fraud
- System Behavior Analysis
- Financial Accounting Fraud
- Healthcare & Dental Insurance Fraud
- Life Insurance Fraud
- Property and Casualty Insurance
- Automobile Insurance
- Worker Compensation & Disability Insurance
The following table outlines the various RADR deployment modes:
RADR with Model Development Needs (RADR-1000)
RADR-1000 is used in cases where a client does not have an existing model. In this case, we work with the client to develop a model and use RADR to provide the insight and visualization.
In one example, Elder Research worked with the U.S. Postal Service OIG to develop a healthcare fraud model. RADR was introduced to strategically visualize the model results, leading to the initiation of 113 investigations and aiding over $9.5 million in recoveries, restitutions, and cost avoidance. The RADR tool amplified the productivity of USPS investigators by reducing the number of hours spent on a case by 30% and increasing the dollars returned per case by 35%.
RADR with Pre-Developed Client Models (RADR- 3000)
RADR-3000 is used in cases where a client has data and a model but needs a server-based visualization tool designed to provide investigative insights. In this scenario, RADR is deployed by the client following our onboarding procedures. As noted in the system requirement section, RADR supports several deployment modes – premise, cloud, Windows, Linux, and more. As a fully supported product, the client has access to administrator and user tutorials and documentation.
RADR and Contracts/US Spending Data (RADR-5001)
Elder Research has developed a Contract assessment model that we have applied to the publicly available US Spend data from USASpending.gov. Elder Research has applied years of contract anomaly experience to the contract information for all federal agencies supported by USASpending.gov.
Elder Research’s model employs several techniques to rate contracts for potential anomalies and incorporate them into an easy to understand score. The higher the score, the more anomalous the contract.
For more information on RADR-5001 and it's use of public data, please check out our blog.
At the heart of RADR is the ability to query your data sources. These questions also act as the fundamental building blocks of a RADR workflow.
Questions can be asked of your data sources using an intuitive drop down menu of elements to the question or as a standard SQL query.
Questions can be saved and shared with other users in the enterprise. A collection of questions can be created in order to provide a unique dashboard for private or selected, enterprise-wide consumption.
From the dashboards and discrete questions, a workflow can be created that is tailored to client needs.
Your data can be assessed by an automated discovery tool to suggest various insights.
- Lease Renewal Risk Model for USPS Office of Inspector General
- Detecting Fraudulent Workers' Compensation Claims
- Improving Unemployment Insurance Claim Fraud Detection
- Detecting Hidden Fraud Risk from Public Data
Download the Data Sheet