Using Predictive Analytics in Experience Studies - PowerPoint Presentation

Slide1

Using Predictive Analytics in Experience Studies

Team: The Game of Life

Charlie Andres, Long Du, Taylor Gallegan, Jessica Santos, Christopher Werner

4/7/17

Uconn Goldenson Center Case Study; Case Study Courtesy of PrudentialSlide2

Project Goals

Using Predictive Analytics in Experience Studies

Identify new, innovative variables that can be used in a predictive model for lapse and mortality rates

Give a brief overview of how variables would be implementedOutline risks and challenges for this approachSlide3

Why Predictive Analytics?

Streamline underwriting process

Cut costsLess invasiveHigher volume and increased processing speed for sales of policiesPrevents human error

Model not prone to biasNo fatigueAvoid “lack of experience” problem

Allows for more precise marketing

Identify individuals more likely to purchase a policySlide4

Known Variables Useful in Predictive Modeling

Riskiness of ProfessionFace Value

Attained AgeGenderPolicy LimitsSlide5

Innovative Variables

Variables were selected based onPotential predictive power

AccessabilityEfficiency Cost effectivenessSlide6

Medical Underwriting

Not optimal to use medical underwritingLengthy

InvasiveNot cost effectivePharmaceutical RecordsQuickerShows ailments that the patient has

Most ongoing problems go with pharmaceutical dataSlide7

Renting vs. Owning a Home

Homeowners are more likely to purchase life insurance

Renters have more of a “temporary” mindset than homeownersCan be applied to lapse rates

Homeowners less likely to make any changes in their life or lifestyle

Leads to less lapse rates for homeowners than rentersSlide8

Credit Score

Credit ScoresLower credit score shows riskier individuals

Study shows higher mortality and lapse go with lower credit scoresEasy and cheap to obtainSlide9

Motor Vehicle Records

Motor Vehicle RecordsShows insight on risky behaviors driving

Could mean risky life choicesReadily available Slide10

Casino Gambling Propensity Score

Predicts the likelihood that an individual will have a gambling addiction based on online and in person visits to casinos and gambling hubs

Available through third party sources

Milliman study showed that this variable has high predictive powerThose who have higher gambling propensity score are riskier individuals, leading to increased mortality and lapse ratesSlide11

Autopay vs. Direct Pay

Most insurers offer options to pay directly or automatic electronic payments

Less likely to lapse automatic payments due to less thought about each payment

Directly billed plans have more opportunities to lapse

VSSlide12

Market Competition

The rate of lapse will be affected whether or not a particular geographic location is more or less concentrated with alternative options for insurance

If there are other insurers in the area, a policyholder may be lured away by a more appealing offer from the competitionSlide13

Product Uniqueness and Flexibility

How innovative and flexible a company's product is could also have an effect on a policyholder’s lapse rate

The flexibility would allow them to change their policy as their needs change as opposed to lapsingSlide14

Geographical Mortality

Grouping or classifying people from the same region in terms of high or low risk of mortality

People living in the same area will likely have similar mortality rates because they face similar conditions Slide15

Wearable Technology

Wearable fitness technology is growing in popularity

More marketableAlready used in the life insurance industry

Policyholders can lower their premiums by living a healthier lifestyle

Activities, gym, doctors

Targets healthier population and deters riskier people

Lower mortality rates with healthier policyholdersSlide16

Churn Scores

A “Churn Score” is a score developed by third party data companies that looks at how often one cancel a phone/bank/TV contract

Identifies consumer loyalty, which is correlated with lapsation

Previous lapse information for the policyholder should be included as wellPrevious lapses indicate future lapseSlide17

Family Member Referral

Millennials

are likely to be loyal to a specific insurance company if a family member uses and values the companyLess likely to depend on policy cost and company reputation than earlier generations

By implementing some type of referral system to identify policyholders referred by a trusted family member, those identified would likely have lower lapse ratesSlide18

Broker vs. Online Purchasing

Those that purchase a policy through a broker they are less likely to lapse

Broker keeps in contact with consumerLarge portion of the broker’s commision relies on the policyholder not lapsingSlide19

Model Building OverviewSlide20

Compiling Data

Collect data in a format so one can perform statistical analysis12-18 month timeframe would remove statistical variation yet keep credibility

Data is from multiple different sourcesSources may not be in same format and difficult to matchNeed to append all sources and match to company’s current databaseSlide21

Building a Dataset

Turn dataset into variables (synthetic and nonsynthetic)Watch out for extremely correlated variables

Look into dataset and perform univariate analysis to confirm the relationships and data make senseMay require you to talk to other business unitsFurther data scrubbing to fix the datasetSlide22

Implementing the Predictive Model

Partition the dataset into 3 sets (train, validation, test)Find the best method to produce a model using train and validation dataset

ex. Stepwise Regression for a Linear/Logit/Probit modelAssess performance of model using “test” datasetImplement the selected ModelSlide23

Monitoring Results

Traditionally underwrite most people after the model is initially implementedAllows one to make sure the model doesn’t open the company up to adverse selection

Can check assumptions on case-by-case basisIt is important to monitor results after the model is implementedImportant to fix issues in the model as quickly as possibleSlide24

Risks and Challenges

Legality; uncertain what is legal under insurance regulationsEthics and social constraints

Cost/difficulty of obtaining variablesSlide25

Conclusion

Predictive Modeling could allow insurance companies to…Streamline underwriting process

Prevent human errorImprove MarketingVariables that we believe may be useful in a model…Age, gender, profession, policy limits, attained ageCredit score, Motor Vehicle records, Pharmaceutical records

Casino Gambling Propensity scoreHow you pay (direct vs. auto)Market Competition, Product Flexibility and UniquenessGeographical Mortality

Wearable TechnologyRenting vs. Owning a Home

Churn Scores

Referred by Family

Where you purchase (online vs. broker)Slide26

Final Thoughts

Questions?

For any further questions, feel free to contact…christopher.werner@uconn.edu

charles.andres@uconn.edutaylor.gallegan@uconn.edu

long.du@uconn.edu

jessica.m.santos@uconn.edu

Thank you to Prudential and the UConn

Goldenson

Center for this opportunity!Slide27

References

[A] Batty, Mike, Arun Tripathi, Alice Kroll, Chen-sheng Peter Wu, David Moore, Chris Stehno, Jim Guszcza, and Mitch Katcher. "Predictive Modeling for Life Insurance."

Deloitte. Deloitte Consulting LLP, Apr. 2010. Web. 10 Mar. 2017.[B] "Climate Effects on Health."

Centers for Disease Control and Prevention. Centers for Disease Control and Prevention, 26 July 2016. Web. 10 Mar. 2017.

[C] Dixon, Pam, and Robert Gellan. "The Scoring of America: How Secret Consumer Scores Threaten Your Privacy and Your Future."

World Privacy Forum

(2014): n. pag. 2 Apr. 2014. Web. 10 Mar. 2017.

[D] Gallup, Inc. "Insurance Companies Have a Big Problem With Millennials."

Gallup.com

. N.p., 05 Mar. 2015. Web. 10 Mar. 2017.

[E] Harker, Patrick T., and Stavros A. Zenios. "Performance of Financial Institutions."

Google Books

. Cambridge University Press, 2000. Web. 10 Mar. 2017.

[F] "How the Vitality Wellness Program Works."

Vitality

. N.p., n.d. Web. 11 Mar. 2017.

[G]

Key Findings from the EY Global Consumer Insurance Survey 2014

(n.d.): n. pag. Web. 10 Mar. 2017.

[H] "National Climate Assessment."

National Climate Assessment

. N.p., n.d. Web. 10 Mar. 2017.

[I] Purushotham, Marianne. "U.S. INDIVIDUAL LIFE PERSISTENCY UPDATE."

Soa.org

. The Society of Actuaries, n.d. Web. 10 Mar. 2017.

[J] Schaber, Ron, Tim Hill, Derek Kueker, Jean-Marc Fix, and Chris Stehno. "Session 8: The Latest on Practical Uses of Big Data and Predictive Analytics."

Soa.org

. The Society of Actuaries, 4 Aug. 2015. Web. 10 Mar. 2017.

[K] Sharps, Kevin, David Hitsky, Stacy Hodgins, and Chin Ma. "Life Insurance Consumer Purchase Behavior."

Deloitte

(n.d.): 96-112.

Deloitte

. Deloitte. Web. 10 Mar. 2017.

[L] Sijbrands, Eric J. G., Erik Tornij, and Sietske J. Homsma. "Mortality Risk Prediction by an Insurance Company and Long-Term Follow-Up of 62,000 Men."

PLoS ONE

. Public Library of Science, 6 May 2009. Web. 10 Mar. 2017.

[M] "2016 Life Insurance Awareness Month."

LIMRA

(n.d.): n. pag. Web. 10 Mar. 2017.Slide28

Bibliography

https://www.the-digital-insurer.com/wp-content/uploads/2013/12/Predictive-Modeling.jpg

http://www.ceremoniesontheshore.com/wp-content/uploads/2017/01/gambling-and-betting.jpghttp://dixon-mgmt.com/wp-content/uploads/2016/09/competition.jpghttps://www.erictyson.com/custom/rent-vs-buy7-436x242.jpg

http://coolefitness.com/blog/wp-content/uploads/2015/11/things-you-can-do-with-wearable-tech-3642-con-768x423-main.png?w=640http://www.propco.com/wp-content/uploads/2015/09/earn-customer-loyalty.jpg

http://www.clipartkid.com/images/303/what-is-a-check-writing-software-3zjrWZ-clipart.jpg

https://nebula.wsimg.com/3d16e64122689a7f247abee067a45245?AccessKeyId=B0A9147ED0ABA5832F78&disposition=0&alloworigin=1

https://blogs-images.forbes.com/benkerschberg/files/2014/09/predictive-analytics-300x200.jpg?width=960

https://www.skipprichard.com/wp-content/uploads/2015/09/bigstock-D-Knob-Maximize-Efficiency-82341836-583x443.jpg

http://www.wellsins.com/wordpress/wp-content/uploads/2015/09/life-insurance-policy.jpg

https://mobilemarketingwatch.com/wp-content/uploads/2016/03/data-1.jpg

http://saveourpostoffice.com/wp-content/uploads/underwriting-services.jpg

http://www.endare.com/wp-content/uploads/2014/10/challenges-ahead-900-x-500-900x407.png

https://www.cdc.gov/heartdisease/images/heart_disease_deaths.png

https://taxistartup.com/wp-content/uploads/2013/06/referral-connection.jpg

https://shawndriscoll.com/wp-content/uploads/2014/04/uniqueness.jpg