predictive analytics

RGA shares basic steps insurers can take to prevent overfitting for more accurate predictive models.

Congress may have forced Mark Zuckerberg to reveal more about personal data gathered on Facebook (FB). But consider this: Your insurance company likely knows a lot more about you. 

The controversy surrounding the political consulting firm Cambridge Analytica’s use of personal data harvested from social media accounts without the users’ permission is among the first of what likely will be a long series of public debates about how the use of “big data” can shape our lives. And one of the most obvious battlegrounds where we should expect such fights to play out soon is in the insurance industry.

Slides from presentations given at the 48th annual M.U.D. Conference have been posted at their website. Presentations include:

• The Population is Abusing Drugs, but Are Drugs Abusing Insurance? 
• Update from the Cuckoo’s Nest: Mental Health Underwriting  
• Electronic Medical Records - State of the Union Update
• The Rise and Fall of Liver Biopsy
• Prostate Cancer- To screen or not to screen that is the question 
• Through Thick and Thin – Red Blood Cell Disorders
• Hypertrophic Cardiomyopathy: Evaluating Those with a Big Heart 
• Using Third Party Scoring in Accelerated Underwriting
• Data Analytics & Underwriting: Are 20th-century regulations still appropriate for 21st-century underwriting? 
• Anti Aging, Youthful Medication, Longevity/HGH 
• Mind the Gap- Understanding the influence of anti-selection and various holes in the underwriting process of accelerated versus traditional underwriting 

Increasingly, computer templates are making binding underwriting decisions through information that is programmed in with final decisions virtually unappealable.  It’s a frustrating situation that is taking the human element out of a very human situation of health and risk assessment.

As life insurers move toward accelerated or low friction underwriting, there is an increased interest in adopting emerging mortality risk prediction scores that are available almost instantaneously. 

Could credit scores have a predictive value on determining subsequent mortality experience? Dean Connor, President and CEO of Sun Life, explained how his company is exploring this question.

The slides from a presentation by Guizhou Hu, M.D. Ph.D., Vice President Chief Decision Analytics Officer (Gen Re) have been posted at the Actuaries' Club of the Southwest website.

The search is on for how to disrupt the underwriting process to find or select the best risks. Can data ever be as good as blood? There is an ever growing number of tools and resources becoming available to insurance companies to underwrite business. The presenters will present some of the tools, data sources, uses and concerns in the underwriting process.

Note: The session above (29) can be found in the 10:30-11:45 a.m. time slot

For those of you fortunate enough to have seen the classic 1967 Academy Award nominated film, “The Graduate,” a line of advice on the future given to Dustin Hoffman’s character is still a classic.  “I want to say one word to you... Just one word... Plastics...”  Nowadays, in the field of life insurance underwriting, that might be expanded to two words: “Predictive analytics.”  If you haven’t heard the term it will certainly become part of the underwriting experience in the upcoming years.