Over the last 5 years, the life insurance industry has experienced an exponential growth in accelerated underwriting (AUW) programs. As the life insurance underwriting process continues to provide less invasive accelerated pathways, insurers increasingly rely on self-disclosed information for key risk factors instead of observed measures under traditional underwriting, such as smoking status and build.
Lisa Seeman, Second VP & Actuary, Biometric Research, and Clinton Innes, Senior Data Scientist, Integrated Analytics, discuss how data science and actuarial monitoring techniques can help manage the increased misrepresentation risk exposure that arises from accelerated underwriting.
This is the fourth webinar in Munich Re’s new five-part North American series exploring innovations in underwriting and data science.
- Misrepresentation risk in AUW: Misrepresentation risk has always been present in the life insurance application process but has increased with accelerated underwriting programs. We explore how risk can be managed through mitigation and monitoring strategies.
- Predictive models as a mitigating strategy: Predictive models and third party data has the potential to mitigate the additional misrepresentation risk arising from waiving traditional underwriting requirements. We examine how application of predictive models can be tailored in accordance to each insurer’s program.
- Monitoring mortality impacts of misrepresentation: How are insurers able to estimate impacts to AUW mortality? We investigate some of the monitoring practices such as random holdout and post-issue APS audits.
Watch a recording of the webinar and download the executive summary for more information.