providers, and retailers, for example,
all strive to tailor product offerings to
individuals after major events such
as a home purchase or the birth of a
child. Provided they have the capacity
to identify those most likely to want
insurance products, insurers similarly
could target fully
underwritten insurance options to
customers at milestones in their lives.
What’s more,
predictive modeling systems and
processes can enable lead-sourcing programs to
balance potential
policyholders in terms of profitability profiles, risk, and retention. Insurers, as a result, will be able to allocate
budgetary outlays more efficiently,
enhance synergies between marketing
and underwriting, and increase acceptance rates of viable policies. They
also can gain a better understanding
of the unique sales and profit potential of given geographic regions.
Underwriting Evolution
Life insurance underwriting tradi-
tionally has revolved around a pro-
cess in which the applicant undergoes
medical and other tests based on a
risk profile that includes the amount
of insurance requested and the ap-
plicant’s age. Many applicants are
required to submit to invasive blood
and fluid tests, electrocardiograms, or
full medical exams. Attending physi-
cian statements often are requested
before a final decision is reached. The
testing typically is both expensive and
time-consuming, sometimes taking
weeks or months to produce under-
writing decisions.
involvement. These underwriting systems provide the added benefit of automatically assigning tasks and cases
to the underwriters based on current
workloads and resource availability. This allows underwriters to focus
on the risk assessment of borderline
cases.
Predictive modeling is a step beyond
automated underwriting. It streamlines and optimizes
underwriting decision-making by
applying business
rules and enhancing traditional
medical underwriting information with relevant external data. This rules-based approach
increases efficiency and produces underwriting decisions more quickly.
Competitive Advantage
The life insurance industry during
the past several years has experienced
pressure to maintain a competitive
product offering and profitable customer base while producing more immediate underwriting decisions for as
many policies as possible. After studying the techniques used in the P/C
sector, leading life insurers are now in
a race to implement automated underwriting and predictive modeling
techniques.
These early adopters rely on internal and external data for important
sets of predictors. External data sets
include prescription history, motor
The evolution of life underwriting for
many companies is likely to accelerate
due to the increased visibility of nonde-
ferrable acquisition costs associated with
unsuccessful sales efforts.
over competitors, some insurers embraced automated underwriting as
a way to lower costs and streamline
processes. In automated underwriting, straight-through processing and
electronic interfaces for policy applications make costly and error-prone
manual data entry unnecessary. Automated underwriting also features
electronic applications and “
drill-down” capabilities. These make it
possible for applicants to answer fewer questions and to complete the application process quickly in instances
in which medical conditions don’t exist. New work-flow tools and business
rules further streamline the process by
automating the ordering of medical
tests and by recommending approval
of (and, in certain instances, approving) applications without underwriter
