SITUATION

 

 

The client company is a long-term care (LTC) closed insurance block. The company recognized that, based on cross-industry insurance fraud estimates, its LTC block was suffering significant financial losses due to insurance fraud, waste, and/or abuse (FWA), which the company had not been able to effectively detect or mitigate. It also recognized that even when FWA had been detected, it was often too late in the claim cycle as months, or even years, of claim payments had already been issued.

​

​

ACTION

 

​

Fuzion sought to understand the root causes as to why the company was experiencing suboptimal fraud identification and mitigation. Fuzion first analyzed the rates and trends for claim referrals, instances of fraud, waste, and abuse, and other characteristics of fraud identification. Based on its evaluation of the company’s fraud and claim data, Fuzion developed a Fraud Mitigation Program tailored to the company’s needs by focusing on increasing the quality of referrals from claim handlers, expanding investigative strategies to better mitigate fraud, and generating referrals based on the output of Fuzion’s fraud identification analytic models.    

 

To effectively implement its customized Fraud Mitigation Program, Fuzion undertook a series of actions. Fuzion started by creating a culture of fraud awareness throughout the claims organization, by way of various grassroots training and engagement strategies for claim handlers at all levels. Removing perceived and actual referral barriers and inspiring handlers to make quality referrals was the top priority. Next, Fuzion concentrated on building cases centered around a variety of investigative strategies. Finally, Fuzion implemented a case conclusion process, which leveraged teams of legal, fraud, and medical experts to ultimately provide recommendations to the company at the conclusion of each investigation to allow it to make the best decision based on the evidence and the company’s risk tolerance. 

​

Concurrent with the above efforts, Fuzion supplemented its referral generation efforts with automated referrals produced by scoring and predictive models. Through the output of customized data models, Fuzion generated actionable referrals based on Fuzion’s proprietary bank of fraud indicators applied to the company’s claims information and relevant external data. 

​

​

RESULT

​

​

The results of these actions were immediate and dramatic, producing more than a 10x increase in fraud identification within the first 12 months of implementation. The company conservatively estimates that it experienced over $2 million of fraud identification and mitigation impact within the first 12 months of program implementation, in addition to unquantifiable impacts in fraud deterrence, prevention, and process improvements.