Underwriting Issues & Innovation Seminar

Transcription

1 The Product Development Section Presents Underwriting Issues & Innovation Seminar July 31-August 1, 2017 The Westin O Hare Chicago, IL Risk Assessment Tools Part 2 Moderator: Cindy Mitchell Presenters: Mike Moran Karen Phelan

2 Application of Credit in Life Insurance TrueRisk Life Society of Actuaries Underwriting Issues & Innovation Seminar JULY 31, 2017

3 TrueRisk Life Introduction A new source for improved risk selection, segmentation and efficient underwriting A credit-based behavioral index predictive of life claims and lapse for use across the life insurance policy life cycle A new piece of evidence that will transform the life insurance industry through unique insights into risk classification and lapse TrueRisk Life was built to accelerate classifying risk to provide a better consumer experience in buying life insurance Reducing overall turnaround time from application to policy Lower underwriting cost in obtaining coverage Provide an assessment of credit-based risk factors that are instructive in the life insurance underwriting process With the growing underinsured middle market, aging distribution group, and increasing consumer demand for instant transactions, insurance carriers need to quickly assess risk with a high level of confidence in a way that does not inconvenience the customer 2016 TransUnion LLC All Rights Reserved 2

4 TrueRisk Life Introduction Considerations in developing the model Purpose To better understand the value of credit data to life insurers and potential applications Background Credit-Based Insurance Scores (CBIS) used in P&C since the 1990 s Wide adoption in pricing & underwriting for auto and home insurance Predictive models built and validated using de-personalized credit data Global risk information provider striving to use information for good Established consumer dispute resolution process Goal of the Model Quantify credit-based behaviors into a life insurance risk score Model transparency provide reasons that influenced risk rating Proactive communication with regulators Balance new data sources with traditional data sources Don t move too fast move as an industry Responsible data custodian Reputation 2016 TransUnion LLC All Rights Reserved 3

5 Big Data Universe Filtered to Get the Most Important Attributes Credit data 800 credit attributes that quantify risk associated with access to credit. 25 credit attributes that quantify behavioral risk associated with credit, foreclosure, bankruptcy and eviction. Data used in the model Demographics Name, Address, DOB and SS# Trades (Loans) Credit Cards, Mortgages, Auto Loans, Personal Loans, Home Equity Loans, Other Debt Hard Inquiries Consumer-initiated applications for credit Public Records Bankruptcies Data NOT used in the model Marketing Shopper (credit card transactions) Social media addresses Household info occupation, education, and lifestyle Checking/savings IRS data Income, race, ethnicity Public Records Criminal Court filings Titles and Licenses Property ownership Professional licenses 2016 TransUnion LLC All Rights Reserved 4

6 TrueRisk Life is Presented as a Score from Higher Numbers Higher Risk Lower Numbers Lower Risk 2016 TransUnion LLC All Rights Reserved 5

7 TrueRisk Life Deliverables Provides the transparent drivers behind the model 1 TrueRisk Life Score 2 Reason Codes 3 Credit Report 2016 TransUnion LLC All Rights Reserved 6

8 Model Creation and Validation v

9 TrueRisk Life Model Creation Credit Report Variables Scores Credit Seeking Activity Credit Tradeline Information Credit Tenure Credit Usage New trades Inquiries Recency & Frequency Severity Recency Count Amount File thickness (e.g. number of active trades) Longevity (e.g. months since oldest trade) Utilization percentage Recency of use Usage patterns The attributes encompass the breadth of the data with the most emphasis on long-run behavior rather than short-term patterns 2016 TransUnion LLC All Rights Reserved 8

10 How the TrueRisk Life Model Was Created Starting Data Variable Selection Model Process External Validation of Model Built the model on 44 million lives and more than 3 million deaths Started with more than 800 variables offering features of individual s credit history Selected variables that were: Most predictive of the outcome Stable over time Non-gameable Not too correlated with the other variables Binary logistic regression Model validated internally using an additional 30 million lives and 2 million deaths Tested model using traditional mortality and lapse studies Used a random holdout dataset of another 16 million lives and 1 million deaths Data comes from de-personalized 1998 credit archive (90% of the U.S. population) Model calibrated to actual deaths occurring over a 12-year period Continuous improvement process as new data sources become available TransUnion built and tested TrueRisk Life on 92 million individuals 2016 TransUnion LLC All Rights Reserved 9

11 Model Validation Population Study Traditional Mortality Study (prepared by RGA) Overall Mortality Details Mortality study performed on holdout sample of 18 million lives using a 1998 TransUnion archive and studying the lives during Score buckets are set to be uniform across the population Study shows 5 times segmentation ( compared to 1-5) SSMDF used as source of deaths; used population mortality tables 2016 TransUnion LLC All Rights Reserved 10

12 Model Validation Insured Lives Study Mortality by Underwriting Class (prepared by RGA) Segmentation exists within risk classes Mortality for highest TrueRisk Life scores (71-100) are over double that of lowest scores (1-10) Non-smokers are shown, but results are similar for smokers Term, UL & VUL; Face Amounts $100,000; Issue Ages < TransUnion LLC All Rights Reserved 11

13 Model Validation Insured Lives Study Lapse by Underwriting Class (prepared by RGA) Segmentation of about 7 times seen in first two durations within given risk class Non-smokers are shown, but results are similar for smokers Term, UL & VUL; Face Amounts $100,000; Issue Ages < TransUnion LLC All Rights Reserved 12

14 TrueRisk Life Industry Validation TransUnion is a National Consumer Reporting Agency with consumer report information on ~220M credit active consumers TrueRisk Life is FCRA compliant TransUnion encourages use with other traditional underwriting evidence TrueRisk Life is a 50 state solution TransUnion and RGA have been proactive and transparent with regulators Presented TrueRisk Life to 4 DOI s (CA, MN, TX, WI) NAIC Life Actuary Task Force call had ~30 state regulators present Over 25 Life Insurance Companies have validated TrueRisk Life through insured lives retrospective studies on 15M policyholders Top 5 US Reinsurance Companies have validated TrueRisk Life 16.8M lives sampled from the US general population anonymized TrueRisk Life Scores 194M Exposure Years (12 Years) 1.1M Consumer Deaths The Reinsurers determined that the TrueRisk Life model is Predictive of mortality Stratifies mortality risk across attributes Segments mortality across income bands Persistency insights 2016 TransUnion LLC All Rights Reserved 13

15 Applications within Life Insurance v

16 TrueRisk Life Offers Options and Flexibility A Different Perspective Complements other sources of data by providing insight into credit-based behavioral risk Combine with Other Evidences Discrete data makes it easy to incorporate with other criteria and automate Apply in a Number of Ways Use the output to make key decisions ranging from underwriting to marketing in compliance with FCRA Dynamic underwriting Further risk segmentation within a Fully Underwritten environment Further risk segmentation within a Simplified Issue environment Batch segmentation ( pre-approval ) for new firm life offers Cross-sell or up-sell existing customers Inforce Policy Management (lapse & mortality) 2016 TransUnion LLC All Rights Reserved 15

17