Hyundai Marine & Fire Insurance(M&F), a Korea-based non-life insurer, is set to deploy a new fraud detection system from SAS, a business analytics software and services.
SAS said that the Hyundai M&F’s fraud detection system combines business rules based on its investigators with model rules generated from data extracted from various IT systems using its advanced statistical techniques.
The models are applied to insurance claims, delivering results to claims investigators in real time. The system also monitors the performance of these rules, enabling the company to quickly modify existing rules or generate new ones.
The predictive models enhance the process of fraud detection so Hyundai M&F can detect insurance fraud not just after it occurs, but prevent a fraudulent claim from being paid.
According SAS, the project will be implemented in three areas. Initially, the fraud pre-detection system to help investigators judge the possibility of fraudulent activities using statistics-based model rules and business rules.
The second area includes a fraud post-detection system to detect afterward the characteristics of certain groups not detected with the prejudgment model and the third with a risk mart to generate data for prejudgment and post-judgment models.
Hyundai M&F Claim Investigation Department team leader Cheol-woo Lee said that with SAS providing the foundation for advanced insurance fraud management, Hyundai can maintain consistent and transparent criteria for investigation, automate the scoring system, and respond swiftly and flexibly to investigations and operations of the organization.
"In particular, this will improve the efficiency of investigation personnel who collect and analyze evidence data for suspected insurance fraud, preventing payment of unjustified claims, while protecting honest policyholders from insurance fraud," Lee said.
SAS Korea director Mi-hye Song said using SAS software improves efficiency of analysts,of fraudulent claims and study evidence data for suspected insurance frauds. It also contributes to increased accuracy of fraud detection without increasing the number of investigators.