Databases Reference
In-Depth Information
For personal auto and commercial auto/fleet, telematics data is becoming
a significant source to generate new insights. Data streaming in from telematics devices
installed in vehicles is providing a bewildering array of information. Miles driven,
location, speed, vehicle performance, driving behavior etc are collected at real time and
are used to improve risk assessment, and offer variable risk based pricing strategies.
Customer-centric Analytics:
Insurers have always taken the approach of a
distributed customer-reach model through agencies, broker networks, self-serving
portals, etc. Due to this distributed model of their business, except the core functions like
policy admin and claims, all of their customer-centric data resides in multiple places.
Therefore, if they need to get a much deeper and more granular understanding of their
customer (both at an aggregate levels as well as at individual customer levels), they will
have to develop data platforms wherein they can bring in data from disparate sources
to create a 360-degree view of their customers. Besides the information available from
agents, brokers, and company employees, insurers also need to consider new sources
of information such as social media sites and external data on demographics and
location-based data. If we take the example of “customer retention” as a business measure,
to develop predictive models to identify such cases where a defection or non-renewal is
highly probable, you will not only need internal data from CRM, Billing, Policy Admin
and Claims systems, you will also need interaction data highlighting relationships and
customer behavior patterns.
A big data analytics platform can also increasingly enable insurers to make customer
decisions in real time at the time of customer interaction. The big data analytics platform
will provide capabilities to analyze web navigation patterns, social media channels of
interactions and preferences, and data entry patterns. Understanding these patterns will
further help to devise automated or human intervention to prospects/customers.
Finance-centric Analytics:
Insurance is a business of risk, hence efficient capital
allocation and optimum investment returns are critical to an insurer's financial
performance. Insurers frequently use custom-built approaches to develop capital asset
pricing models (CAPM) to value and manage assets for least risk and maximum return.
Compliance and Regulatory requirements like Solvency II mandates insurers to develop
sophisticated models to address areas such as asset/liability matching, investment
portfolio optimization, embedded value calculations, and econometric modeling. An
increasingly complex business and economic environment is pushing insurers to do
more with analytics so that they can dynamically manage the business. Consider the
value of being able to combine real-time insight from the operational side of the business
with extensive external information concerning macroeconomic attributes and then
being able to view risks across portfolios within hours or even minutes.
We end this section with Figure
3-9
, showing the analytics architecture and some use
cases in the insurance field.
