Professional Documents
Culture Documents
WHITE PAPER
SAS White Paper
Table of Contents
Executive Summary. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
Introduction. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
Distribution and Producer Analytics. . . . . . . . . . . . . . . . . . . . . . . . . . . 2
Producer Segmentation. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
Territory Definition and Route Optimization. . . . . . . . . . . . . . . . . . . . . . 3
Lead Generation. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
Maximize Wallet Share: Cross-Selling. . . . . . . . . . . . . . . . . . . . . . . . . . 3
Optimize Marketing Offers. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
Compliance and Suitability . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
Profitability and Lifetime Value. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
Customer Analytics. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
Social Media Analytics. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
Customer Interaction Management. . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
Product Lifecycle Management. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
Product Underwriting. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
Product Development . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
Product Profitability. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
Product Lifecycle Management. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
Operational Analytics. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
Call Routing. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
Predictive Alerts and Triggering Events. . . . . . . . . . . . . . . . . . . . . . . . . 9
Conclusion. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
The Analytical Life Insurer
Executive Summary
In the insurance industry, the companies that focus on product lines typically under the
diversified insurance umbrella (such as group and individual life, annuities, retirement
plans, financial services and supplemental health products) have been slow to adopt
predictive analytics within their organizations. Other industries, including property
casualty insurers, continually demonstrate success in using analytics to grow their
businesses more profitably and increase revenue while managing risk. Life insurance
executives are beginning to recognize the need to evaluate analytics as a way to
innovate, differentiate and improve their organizations. This paper will uncover business
strategies enabled by analytics, and provide examples of analytic innovation that insurers
can introduce in their business processes.
Introduction
The business drivers for considering an analytic strategy within the industry are
compelling: Due to continuing low interest rates which lead to a decline in investment
yields, the uncertainty of the regulatory environment, the commoditization of products,
competitive industry pricing and a soft economy, insurers are feeling increased pressure
on profitability. In addition, insurers are aggressively competing for awareness and
wallet share among distributors, producers and customers. It’s critical to identify
ways to optimize their field organizations; find the most profitable agents, brokers and
customers; optimize workflow while decreasing costs; and balance risk and regulatory
demands.
The analytic strategies that life insurers can employ are divided into four representative
categories (figure 1):
1
SAS White Paper
Producer Segmentation
In a representative scenario, while insurers have employed basic segmentation
techniques, these segments are not predictive. Some wholesaling organizations group
producers into simple classifications and align sales activities with “higher-value”
segments. The problem with this segmentation strategy is their rearview-mirror definition
of value.
One insurer had a campaign for producers that hadn’t sold any business in
the prior six months. Using predictive modeling, the organization was able
to create a model that would predict which producers would stop selling
before they did stop. It implemented a number of marketing campaigns
targeted to the at-risk group of producers, resulting in a multimillion-dollar
2
The Analytical Life Insurer
Lead Generation
The most common use of predictive analytics for captive distribution models is to
provide leads to the producers. Insurers with this capability are combining their internal
data with third-party database marketing solutions to mine their own books of business
for opportunities.
3
SAS White Paper
“We’re able to target our customer segments much more logically and
granularly. We’ve identified about 25 separate cells, and we see their
demographics and previous transaction behaviors. That lets us tailor
specific cross-sell offers and script different contact scenarios based
on their value, their propensity to buy, their propensity to pay, and their
propensity to lapse… In the first quarter after implementing SAS, sales to
existing customers jumped to more than 20 percent,” Karthikeyan said.
4
The Analytical Life Insurer
past five years. Regulatory agencies have aggressively moved to protect consumers
from poor or questionable sales practices at the distribution and insurer levels.
One insurer using lifetime value scoring changed the evaluation criteria for
its direct mail marketing campaigns. Where it used to measure success
based on the number of responses and the close rates, it’s moved to a
model where it can differentiate based not only on the number of sales,
but the quality of those sales. Going even further, it expanded lifetime
value metrics to drive not only the placement of its captive agency sales
force, but how those agents were compensated. Compensation now takes
into account the quality of the customer relationships that the agents are
bringing to the insurer and rewarding them for it.
Customer lifetime value metrics help the insurer understand which producers and
customers are driving greater value than others. When it identifies the differences
between profitable segments, it can create programs to increase those success factors.
This particular insurer increased return on investment for marketing campaigns by 14
percent and saw significant enhancements in agent performance. Even in the absence
of a true CLV metric, even a simple profitability metric can drive results:
5
SAS White Paper
Customer Analytics
Insurance companies must meet the demands of consumers in tech-savvy younger
generations as well as manage the needs and requirements of the large global
population approaching retirement age. Demographic and ethnographic shifts affect
these organizations’ internal workforce as well as distribution partners and consumers,
pressuring insurers to effectively create and manage services that they can deliver at
multiple levels, through multiple channels. Pervasive consumer technologies are driving
change throughout the insurance industry.
• Finding market opportunity through identifying new target audiences, or inputs into
product development.
• Executing on opportunity through campaign management to target new
prospects.
• Brand management.
• Using social media data in other non-marketing activities, such as underwriting,
customer service, risk management and fraud.
The growth in customer interaction channels – mobile, Web, phone, mail, face-to-
face – necessitates a careful choreography of interaction points. Some insurer industry
innovators are using the mobile and Web channels to reach out to untapped market
segments.
AXA Equitable launched a life insurance game app for Apple’s iPad ® and
iPhone® mobile devices called “Pass It On!” The app is designed to educate
consumers on the benefits of their indexed universal life products at
different life stages through an interactive game (prospective customers are
offered a chance to win the “Pass It On!” sweepstakes). Mobile applications
are providing insurers with new interaction channels to engage with and
educate potential customers.
6
The Analytical Life Insurer
Another insurer undertook a strategic initiative to better serve its financial advisor and
client networks, including service and channel segmentation to better find and grow
new investors that may not have been served in the past. In order to gain the capacity
needed to implement this strategy, it employed its call center to help achieve this goal.
Real-time customer profiling and interaction management at the time of contact became
a cornerstone of its strategy. Other initiatives included:
Product Underwriting
The average time from the start of the underwriting process to policy issuance for a
mid- to high-value life insurance policy is 72 days. The sales cycle is so long that many
advisors don’t want to deal with the complexity of the sale, and potential customers
don’t want the hassle of the medical reviews. With life insurance sales at a 50-year low,
insurers are rushing to find ways to make the products easier to buy and sell. One of the
most innovative ways that insurers are changing the underwriting process is by creating
models to predict whether further medical tests are needed. The underwriters use the
models as a guideline for ordering additional tests. If no tests are needed, the policy can
be quickly issued. The models are developed using third-party consumer data sources
to identify risky attributes.
Product Development
Insurers are increasingly recognizing the need to differentiate their product development
approach, particularly in group insurance products. One insurer just finished the design
of a new retirement product that incorporated more than 500 rating variables. In addition
to new product features and compensation structure, the granularity of the rating
structure allows for personalized individual plan pricing. This personalized approach
makes the product a more attractive offering for both producers and plan sponsors.
7
SAS White Paper
Product Profitability
Other insurers are actively implementing analytic models to determine product
profitability that gives a signal in advance whether adjustments should be made to
product lines.
Canadian insurer The Standard Life Assurance Company opted for SAS
Activity-Based Management, an analytic application that models business
processes to determine cost, profitability and the drivers that help
organizations make informed decisions that streamline operations, deliver
revenue growth and reduce costs across the organization. “SAS Activity-
Based Management software gives us a sense of which products we should
focus on and which ones we should focus less on,” says Eric Campbell,
Manager of Financial Strategy and Planning, “Further, we can calculate a
product’s efficiency and improvement over time.” The solution gives insight
not only into which product is most or least profitable, but also where more
investment may be required over time, and is considered crucial to doing
business.
Operational Analytics
Operational analytics covers a broad spectrum of initiatives within the diversified life
insurance industry, and can cover areas such as workforce and workload optimization,
call center analytics and fraud detection. The following are three real-world examples of
operational analytics in the life insurance industry.
Call Routing
The call center is the first line of defense in retention efforts. As a system for effectively
matching an incoming call with the appropriate CSR, skills- and trigger-based routing
have gained in popularity over the last decade. In one insurer’s customer retention
program, a predictive model was built to identify “at-risk” policyholders. If the
policyholder called the call center and was deemed to be at high risk, he or she would
be automatically routed to a retention specialist.
8
The Analytical Life Insurer
Conclusion
Insurance companies operating in their status quo business model will be at a
competitive disadvantage in the coming years. Increasingly, insurers must provide
unique products and services tailored to meet the diverse needs of their producer
and consumer communities. To do so, they need a deep understanding of complex
customer behaviors, market segments and product life cycles. The ability to capitalize
on these new market opportunities will depend on an insurer’s adeptness at identifying
new customers and producers and retaining profitable ones, providing the right
products at the right time, and giving customers top-level service through multiple
delivery channels. Analytics represents the next frontier for this industry, and even with
the challenges posed in shifting from a sales culture to an analytic culture, the industry is
well-positioned to start down this path.
9
About SAS
SAS is the leader in business analytics software and services, and the largest independent vendor in the business intelligence
market. Through innovative solutions, SAS helps customers at more than 55,000 sites improve performance and deliver value by
making better decisions faster. Since 1976 SAS has been giving customers around the world THE POWER TO KNOW®.