Session 60 PD, Predictive Modeling Real Applications in Life Insurance and Annuities. Moderator: Ricardo Trachtman, FSA, MAAA

Transcription

1 Session 60 PD, Predictive Modeling Real Applications in Life Insurance and Annuities Moderator: Ricardo Trachtman, FSA, MAAA Presenters: JJ Lane Carroll, FSA, MAAA Allen M. Klein, FSA, MAAA Scott Anthony Rushing, FSA, MAAA

2 SOA Life and Annuity Symposium Session 60: Predictive Modeling Real Applications in Life Insurance and Annuities Predictive Analytics and Life Underwriting Al Klein May 5, 2015

3 Definitions Big data Predictive analytics Predictive analytics Process Why you should use it Agenda Milliman example of approach to underwriting using both traditional and non-traditional data The future Concluding thoughts 2

4 Definition Big Data Big data is like xxxxxxx xxx: Everyone talks about it, nobody really knows how to do it, everyone thinks everyone else is doing it, so everyone claims they are doing it. Dan Ariely Big data is what can be used with predictive analytics to better analyze data and make decisions Big data can include your own data and/or external data 3

5 Definition Predictive Analytics Process in which current or historical data or information are used to predict future events or behaviors We have been doing this for years in life insurance: Underwriting assessment Preferred underwriting criteria Expected mortality assumptions What s new? More sophisticated modeling techniques and capabilities More data is available, both insurance- and noninsurance-related 4

6 The Big Picture: Big Data Analytics in Financial Services May 2014 report by LIMRA from online survey of 44 companies Some of findings: 9 of 10 life insurance companies reported using big data analytics One-third have had programs in place for more than 10 years Most companies have fewer than 10 people dedicated to their big data analytics program Implementation hurdles include: Funding Executive buy-in Legacy systems Staffing 5

7 Predictive Analytics Process Statistical / predictive models used, several examples: 6 Classification and Regression Trees (CART) Sorts data/populations into smaller branches/nodes, used to predict a response Cox Proportional Hazard Estimate of the relative value/risk Generalized Linear Model (GLM) Expands on linear regression model variable constant to observed values Allows for a better understanding of the ways multiple variables interact in a non-linear way and that may not be obvious Neural Networks Model/function which uses interconnected neurons to compute values from a large number of inputs Regression splines A function connected piecewise through polynomial functions to create smoothness where the polynomial pieces connect Main purpose is to predict an outcome variable from a set of independent or predictor variables Statistical model should be validated

8 7 Why use Predictive Analytics? More sophisticated analysis usually provides better information and solutions Better likelihood of optimizing desired outcome May find new solutions or opportunities Helps to find new and/or better customers Helps to detect fraud Other industries are using it What are the downsides for life insurance purposes? Results need to be explainable With respect to lifestyle analytics, are buying habits real?

9 Are buying habits real? From a well known underwriter, based on my purchasing habits and lifestyle, I may be: Over age 70 Socio-economically challenged Weight challenged Addicted to chocolate Drinking too much Smoking too much Having a few health issues 8

10 Uses of Predictive Analytics in Life Insurance Selection of agents Lead generation Underwriting Product development Policyholder retention Detection of fraud at claims time In force management 9

11 What Data is available today? Insurance data 10 Gender Age Height/weight Geographic location Medical history Financial information Lifestyle information Driving record Consumer data Thousands of records on every individual While geographic data exists and is predictive, desire is generally to use individualized consumer data Will discuss consumer data in more detail in Milliman example

12 Milliman Example A client asked us to develop a model, using consumer data to determine who would qualify for the best preferred class Goal was to be able to waive paramedical exam A secondary task was to determine who would be most likely to be declined Reasons for this request: Reduce underwriting costs by eliminating need for medical exams, MVR, and other tests in some cases Reduce issue time Improve customer satisfaction Reduce not-taken rates, leading to additional savings 11

13 Milliman Example (cont d) Worked closely with client, who provided us data (about 70,000 lives) Some data used to develop a model and rest saved to later validate the model Used a machine-learning program Finds non-linear behavior and interactions that a generalized linear model (GLM) cannot Recognizes variables that have strong fit Decision trees used At each node, many factors are determined and those that are the strongest drivers are used to split the policies at that node 12

14 Milliman Example (cont d) Example of a node split All Policies: 10,000 Probability of Best Preferred: 35.0% BMI = 29 or more: 2,162 policies Probability of Best Preferred: 6.6% BMI = < 29: 7,838 policies Probability of Best Preferred: 42.9% 13

15 Milliman Example (cont d) Ultimate goal was to develop a model that produced a score for each applicant Score was used to determine if the applicant could be issued a policy without further underwriting Considered both traditional and non-traditional variables Examples of traditional variables Age BMI Gender MIB MVR Rx histories 14

16 Milliman Example (cont d) Examples of non-traditional variables 15 Prevalence of banking Prevalence of exercise Home assessed value Household income Net worth Propensity to buy brand-name medicine Prevalence of shopping Travel These variables were among 350 fields of data considered, which were culled from the thousands of pieces of data available Note that some of the variables were created from multiple pieces of data Some can move the scoring in either direction, depending on the circumstances (e.g., shopping)

17 Milliman Example Scoring Process Want to determine whether the policy can be rapidly issued based on the score (without further underwriting) Need to establish cut-off points for bucketing the lives into each of the underwriting classes (e.g., best preferred, preferred, standard, decline) Limits were set to reduce the number of cases where the applicant received a lower rating than from the normal best preferred underwriting risk class We used two thresholds: No more than 20% of applicants one class below class being studied could score above the threshold being tested No more than 10% of applicants more than one class below class being studied could score above threshold being tested 16

18 Milliman Example Validation Process 70% of data was used to construct the model and 30% was set aside to validate the model after it was constructed Both models (probability of best preferred and probability of decline) had a validation correlation of over 99% Correlations over 90% are considered good fits to the underlying data 17

19 Milliman Example Scoring Results A small percentage of policies would be issued under this program who would have otherwise been declined However, this should be more than offset by the underwriting savings from the policies that are rapid issued 18

20 Milliman Example Other Findings Traditional factors are stronger predictors for determining the best preferred class Consumer and financial factors are more influential in determining whether or not to decline It was estimated that almost 80% of the top applicants could be rapid issued under this program However, score level could be set wherever company chooses The additional non-insurance data proved predictive, but was most valuable when used with the insurance data (i.e., MIB, MVR, Rx) 19

21 20 The Future Big Data, Predictive Analytics, and Life Insurance Electronic Health Records (EHR) and Electronic Medical Records (EMR) Social media Using big data to fight dementia and Alzheimer s, The Globe and Mail, September 15, 2014 J. Craig Venter plans to amass and electronically analyze medical, genomic, and metabolic data of 40,000 individuals every year Genetics InnerAge blood test Wearable technology

22 Health-Related Wearable Technology Some of these are here today. Some will be in the future. Wrist band that tracks fitness (steps, fuel, versus friends, light beams) Headband to calm your mind and keep you focused Do an x-ray, eye and ear exam, ultrasound through your phone App for measuring obstructive sleep apnea by putting your finger in a sensor and wearing it overnight Contact lens that measures glucose levels through tears Band-aid that records every heartbeat for two weeks Put a chip in your bloodstream to warn of a heart attack in the next few days to a couple of weeks Vest that has a defibrillator for those at risk for sudden cardiac arrest Bra that detects breast cancer Sweat-wicking gym shirt with 14 muscle-movement sensors, 2 heart rate sensors, and 2 breathing sensors Fabric that doesn t need washing, can change shapes and colors, reacts 21 to the environment, is conductive, could be part of the digital environment

23 Concluding Thoughts If not already doing so, begin to keep track of your own detailed data Collect everything (e.g., lab results, physical measurements, ratings, face amount purchased, birthdates, issue dates, claims dates, etc.) Look to see how you can best use it If we, as an industry, do not use the information available to us, someone else will Thank you! 22

24 23 Bio Al Klein Al is a principal and consulting actuary with Milliman s Bannockburn/Chicago office. He joined in Al s primary responsibilities include industry experience studies and helping clients with mortality, longevity, and underwriting related issues. This may involve product development, assumption setting, and mergers and acquisitions. Al s expertise on mortality and underwriting includes traditional products, simplified issue, final expense, older age, and preferred. Prior to joining Milliman, Al worked for a large stock life insurance company where he was responsible for experience studies across all lines of business. He has also worked for other life insurance companies, a reinsurer and consultant, where he has been responsible for strategic planning, product development and traditional reinsurance aspects of the business. Al is a frequent speaker at industry meetings and currently involved with a number of industry activities, including: SOA representative and co-vice Chair for the Mortality Working Group (MWG) of the International Actuarial Association MWG Underwriting Sub-group chair goal is to study underwriting done around the world SOA Longevity Advisory Group SOA Mortality and Underwriting Survey Committee Joint American Academy of Actuaries (AAA) / Society of Actuaries (SOA) Preferred Mortality Oversight Group Joint AAA / SOA Underwriting Criteria Team 2014 SOA Valuation Basic Table (VBT) Development Team SOA Longevity Calculator Development Team Longer Life Foundation Advisory Board Al received a Bachelor of Science degree in Actuarial Science and Finance from the University of Illinois, Urbana. Contact information: (312) , al.klein@milliman.com

25 Credit Models for Life Insurance Predictive Modeling Real Applications in Life Insurance and Annuities SOA Life & Annuity Meeting New York, NY May 1, 2015 Scott Rushing FSA, MAAA RGA Reinsurance Company Head of Global Research

26 Purpose Introduction RGA & TransUnion partnered together 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 are built and validated using de-personalized credit data Goals of the Model To predict mortality The model is also extremely good at predicting lapses 2

27 Credit Reporting Process Introduction Data flow from the consumer transactions / behaviors to the credit report Consumer Collection Agencies Courts Lender / Creditor #1 Lender / Creditor #2.. Lender / Creditor #10 Utilities Etc. TransUnion Consolidates data, builds models Comprehensive reports on individuals (Scores, Attributes or Full file) Consumers Landlords P&C Insurers Life Insurers Lenders Utilities Collection Agencies Employers (new hires) 3

28 Model Creation Building the Model Data comes from de-personalized 1998 credit archive (90% of US pop) Model calibrated to actual deaths occurring over a 12-year period Starting Data Variable Selection Modeling Process External Validation of Model TU TrueRisk Life Score Built the model on 44 million lives and >3 million deaths Started with >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 Age, Gender and Region used as control variables Tested model using traditional mortality and lapse studies Used a random holdout dataset of another 18 million lives TransUnion TrueRisk Life presented as a score from: 1 to 100 Low Risk High Risk 4

29 Population Study Model Validation Population Study 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 A/E Results (Adjusted Basis) 250% 200% 150% 100% 50% Overall Mortality Population Study 0% TU TrueRisk Life Score 5

30 By Age (as of ) Model Validation Population Study Similar shape curves by age band, but the curve is slightly flatter than the others 300% 250% Mortality by Age Group Population Study A/E Results (Adjusted Basis) 200% 150% 100% 50% 0% TU TrueRisk Life Score

31 By Duration Very similar results by duration Model Validation Population Study A/E Results (Adjusted Basis) 300% 250% 200% 150% 100% 50% Mortality by Duration Population Study 0% TU TrueRisk Life Score

32 Insured Data Study Model Validation Insured Lives Study Important to test the value of TRL on an insured block of business Details of the Study Business Studied: Full UW (term, UL, VUL) and small face WL Study Period: Mortality and Lapse result studied on a count basis Relative mortality and relative lapse results reported 35% 30% 25% 20% 15% 10% 5% 0% Distribution of Insureds (Compared to Population) TU TrueRisk Life Score Population (< age 70) Full UW 100+ (< age 70) WL <100 (< age 70) 8

33 Model Validation Insured Lives Study Fully Underwritten Mortality Study Details: Term, UL and VUL; Face Amount $100k; Issue Ages < 70 Results: Mortality of group is 2.6 times higher than 1-10 group Relative Mortality 250% 200% 150% 100% 50% Overall Mortality Issue Age < 70 Claim Count 0% TU TrueRisk Life Score Claim Count Relative Mortality 9

34 Model Validation Insured Lives Study Fully Underwritten Mortality Study Details: Term, UL and VUL; Face Amount $100k; Issue Ages < 70 Results: Segmentation exists within risk classes; Mortality for worst TRL scores (71-100) are about double that of best risks (1-10); Most relevant splits may vary by risk class; Non- Smokers are shown, but results are similar for smokers. 250% 200% Mortality by Underwriting Class Issue Age < 70 Relative Mortality 150% 100% 50% 0% Claim Count Preferred NS Non-Preferred NS Substandard NS TU TrueRisk Life Score Claim Count Relative Mortality 10

35 Model Validation Insured Lives Study Fully Underwritten Lapse Study 9,00 0 8,00 0 7,00 0 6,00 0 5,00 0 4,00 0 3,00 0 2,00 0 1, , , , , ,0 00 8,00 0 6,00 0 4,00 0 2, Details Term, UL and VUL Face Amount $100k Issue Ages < 70 Results Lapse rates of group is 6 times higher than 1-10 group in durations 1-2 Continued segmentation seen in later durations, but less dramatic Similar results seen when looking at the curves by issue age band Relative Lapse Rate Relative Lapse Rate 700% 600% 500% 400% 300% 200% 100% 0% 250% 200% 150% 100% 50% Overall Lapse Results - Durations 1-2 Issue Age < TU TrueRisk_Life_Score Lapse Count Relative Lapse Rate Overall Lapse Results - Durations 3 + Issue Age < 70 Lapse Count Lapse Count 0% TU TrueRisk_Life_Score Lapse Count Relative Lapse Rate 11

36 Model Validation Insured Lives Study Fully Underwritten Lapse Study 4,00 0 3,50 0 3,00 0 2,50 0 2,00 0 1,50 0 1, Details: Term, UL and VUL; Face Amount $100k; Issue Ages < 70 Results: Segmentation of about 6 times seen in first two durations within given risk class; Non-Smokers are shown, but results are similar for smokers Relative Lapse Rate 800% 700% 600% 500% 400% 300% 200% 100% 0% Lapse Results by Non-Smoker UW Class Durations 1-2; Issue Age < Preferred NS Non-Preferred NS Substandard Non-Smoker TU TrueRisk_Life_Score Lapse Count Relative Lapse Rate Lapse Count 12

37 Model Validation Insured Lives Study Small Face Whole Life Mortality Study Details Includes Whole Life products < $100k face; most of this business is under $25k or $50k Issue Ages < 70 Scores above 90 are further split out Results Mortality about 6 times higher for worst scores Segmentation at higher scores for this business 14% of exposure & 29% of claims have score > 95 > 10% of the claims have a score of 100 Value also seen beyond age 70 Relative Mortality 350% 300% 250% 200% 150% 100% 50% 0% Overall Mortality Issue Age < TU TrueRisk Life Score Claim Count AE 08VBT CNT Claim Count 13

38 Model Validation Insured Lives Study Small Face Whole Life Lapse Study 5,00 0 4,50 0 4,00 0 3,50 0 3,00 0 2,50 0 2,00 0 1,50 0 1, ,00 0 1,80 0 1,60 0 1,40 0 1,20 0 1, Details Includes Whole Life products < $100k face; most of this business is under $25k or $50k Issue Ages < 70 Results Significantly higher lapse rates at the higher scores Raw lapse rates are much lower for durations 3+, but there is little segmentation by score Relative Lapse Rate Relative Lapse Rate 400% 350% 300% 250% 200% 150% 100% 50% 0% 200% 150% 100% 50% Overall Lapse Results - Durations 1-2 Issue Age < TU TrueRisk_Life_Score Lapse Count Relative Lapse Rate Overall Lapse Results - Durations 3 + Issue Age < 70 Lapse Count Lapse Count 0% TU TrueRisk_Life_Score Lapse Count Relative Lapse Rate

39 Sample of Applications Batch segmentation ( pre-approval ) for new firm life offers Underwriting Triage Risk Segmentation (beyond traditional medical factors) Modification of existing UW requirements Cross-sell or upsell existing customers Inforce Policy Management (lapse & mortality) 15

40 Questions?? Scott Rushing FSA, MAAA RGA Reinsurance Company Vice President and Actuary Global R&D Head of Global Research 16

41 Predictive analytics case studies SOA Life and Annuity Symposium Session 6 0 : Predictive Modeling Real Applications in Life Insurance and Annuities JJ Lane Carroll May 5, 2015

42 My favorite de finition of pre dictive analytics Indiana Department of Revenue Confirmed Regular processing of returns Verification Ta xp a ye rs required to take Identity Confirmation Quiz Fraudulent Clear fraudulent cases sent to special investigation unit The State of Indiana stopped $88 million in attempted tax fraud in

43 Predictive analytics examples Case Study #1: Underwriting Case Study #2: Marketing Case Study #3: Epidemiology

44 Case study # 1 : Underwriting 4

45 Smoker model example Non-Smoke r within defined threshold Fast Tra c k Additional information needed Alternate Tools / Traditional process Smoke r within defined threshold Traditional process Non-smoker rate Non-smoker rate Smoker rate Smoker rate 5

46 Evaluating the performance of a model Receiver operating characteristic (ROC) curves can be used to assess the absolute performance of predictive models or compare the performance of several models. The higher the Area Under the Curve, the more predictive the model. A value of 0.5 basically means the probability of the event being predicted for a particular applicant is no better than tossing a coin. An AUC above 0.9 is highly predictive. What does this mean for insurance decisions? 6

47 Case study #2: Marketing 7

48 Information overload Behavioral economics: information overload prevents decision making Potential to increase sales simply by getting the: Right product Right message In the right way At the right time To the right person 8

49 Predictive model for marketing segmentation More art than science No clean breaks between segments Attitudes change Close still works 9

50 Case Study #3: Epidemiology 10

51 Etiology Big Data Smoke r Lun g Cance r Smoke r Smoke r Smoke r Causation Replaced by Correlation 11

52 Social Media Chronic Diseases Map Diseases 12

53 Questions 13

54 14

55 Legal notice 2015 Swiss Re. All rights reserved. You are not permitted to create any modifications or derivative works of this presentation or to use it for commercial or other public purposes without the prior written permission of Swiss Re. The information and opinions contained in the presentation are provided as at the date of the presentation and are subject to change without notice. Although the information used was taken from reliable sources, Swiss Re does not accept any responsibility for the accuracy or comprehensiveness of the details given. All liability for the accuracy and completeness thereof or for any damage or loss resulting from the use of the information contained in this presentation is expressly excluded. Under no circumstances shall Swiss Re or its Group companies be liable for any financial or consequential loss relating to this presentation. 15