6 JUNE 2019
Talex Diede
Life Insurance Market Segmentation
Motivation
Predictive Analytics Journey
3DIFFICULTY
VALU
E Descriptive Analytics
Diagnostic Analytics
Predictive Analytics
Prescriptive Analytics
What happened?
Why did it happen?
What will happen?
How can we make it happen?
Source: Gartner (March 2012)
4
Market segmentation and targeted marketing in your life
5
Financial usage of segmentation
6
Segmentation is already happening in insurance
7
Current paradigm in life insurance
Customer segmentation in life insurance
• Understand the needs of the customer
• Build tailored products
• Efficiently market existing products
• Improve customer retention
Segmentation for Life Insurance
Current view of customers
10
Susan is a 65 year-old female and has a qualified tax status
Susan
Kathy is a 65 year-old female and has a qualified tax status
Kathy
Mary is a 65 year-old female and has a qualified tax status
MaryTheoretically… Kathy, Susan, and Mary look identical, are assumed to behave in the same way, and have the same value and risk profile.
In Reality…• Do they really behave the
same?• Do they have the same
needs?• How much does the value
and risk profile of each customer vary?
• How can you acquire and retain the best customers?
Understanding your customers
11
Major types of segmentation data
GeographicDemographic Psychographic Behavioral
12
13
Data enrichment provides a comprehensive view
Ensure segments are useful
Measurable Substantial AccessibleDifferentiable Actionable
14
Example of data-driven segments that identify policyholders likely to behave in similar ways
15
Retired:Likely to be older, and live in areas with high proportions of individuals over the age of 65
Middle Income:Slightly higher than average education levels, home values, and income levels
Lower Income:Lower than average education levels, home values, and income levels, newer homeowners
Settled:Married, owned their homes for a long time, low loan-to-value ratios, lower home values
In Debt:Low credit scores, high counts of credit delinquencies in the last five years
Renters: Unlikely to own their own homes
High Income:Highest education levels, home values, and income levels
What to do with segmentation
Create segmented behavior assumptionse.g. Lapse
17
Unsegmented
Unsegmented
Debt
Debt
Retired
Actuarial projection to determine profitability
18
Customer Level Profitability (CLP)
Calculate profitability measure at seriatim level
Cash Flow Projection Model
Project seriatim cash flows
Customer Profile
Implement customer segment level behavior assumptions
Enhanced view of your customers
19
Susan is 65 years old and has a qualified tax status
Susan is also retired, but she lives in Georgia where she has owned her home for 30+ years now
Susan is identified as belonging to the “Settled” segment
Susan tends to have high persistency in her product
Susan
Kathy is 65 years old and has a qualified tax status
Kathy is retired, and she currently lives in Florida in a community of other retired folks
Kathy is identified as belonging to the “Retired” segment
Kathy tends to be the most sensitive to the value of the guarantees in her product
Kathy
Mary is 65 years old and has a qualified tax status
Mary is not yet retired, she lives in the San Francisco bay area and has high income and net worth
Mary is identified as belonging to the “High Income” segment
Mary is less likely to use the liquidity features in her product
Mary Knowing… How could this new view of your customers be used?
Actuarial• Product design• ALM/Hedging• Inforce management• Solvency & risk
Sales & Distribution• Firm selection• Wholesaler lead scoring
Marketing• Driving demand• Cross-selling
Identify regions to focus marketing based on segmentation
20
Target policyholders for retention
21
Noaction
Noaction
Target for retention
Consider buyback
Policy 1
Policy 2
Policy 3
Policy 4
Policy 5
Probability of lapse
Prof
itabi
lity
Target messaging and products for different phases of life
22
Important Considerations
Things to keep in mind or investigate for this kind of work
Use case Data availability Regulations
FCRAHIPAAGDPRNY Circular letter No. 1
24
Looking forward
Move beyond segments to individual people
26
Questions?