As digitization and automation rapidly progress in today’s life and health industry, issues with misrepresentation during the insurance application process are also becoming a growing concern for insurers around the globe. SCOR’s recent misrepresentation survey finds that misrepresentation in application forms costs the average insurance customer an estimated 5% to 10% in higher premiums. 

In order to reduce this risk, SCOR works closely with insurers to find and correct areas of misrepresentation, consults post-issue sampling, reviews the automated underwriting processes, and monitors the quality of financial advisory firms. 

To further improve the quality of analysis and provide client insurance companies with an innovative advanced solution to detect and reduce misrepresentation, SCOR developed  predictive disclosure modeling, which harnesses readily available underwriting data to analyze misrepresentation. This modeling helps SCOR and insurers understand various drivers for disclosure rates and areas of misrepresentation. 

This modeling brings multiple advantages to various stakeholders in the life insurance journey, including improved risk selection, claims experience, and reinsurance terms for insurers. For customers, it leads to increased certainty of coverage, payout of the claim, and ultimately lower premiums on average.  

This article gives an overview of the disclosure modeling process at a high level as well as the technical details of a standard approach to disclosure modeling that SCOR has implemented with various life insurers: data cleaning, standardization, visualization, and predictive modelling.