Page 24 - Insurance Times March 2021

It also achieved a 57 percent increase in accuracy in fraud through a fraud detection algorithm before sending wire
detection from the previous year. From fraud detection to instructions to the bank to pay for the claim settlement.
underwriting, AI technologies are reimagining every facet
of APAC's booming insurance industry. By reducing the risks Advanced underwriting:
and streamlining processes, it can help companies drive
IoT and tracking devices yield an explosion of valuable data
efficiencies and deliver more personalized products and which can be utilized to make the process of determining
services - the key to future success.
insurance premium upright and regulated. Fitness and
vehicle tracking system in both health and auto insurance
From smart chatbots that offer quick customer service round sector give rise to the dynamic, intelligent underwriting
the clock to the array of machine learning technologies that
algorithms that cleverly control the way premium is
spruce up the functioning of any workplace through its
dictated. Using Artificial Intelligence and Machine Learning,
automation power, the expanding potential of Artificial insurers can save a lot of time and resources involved in
Intelligence in Insurance is already being used in many ways, underwriting process and tedious questions and surveys, and
as covered in our last blog. With increased awareness and automate the process. Insurance bots can automatically
resources about the game-changing influence of AI in the
explore a customer's general economy and social profile to
Insurance industry, the initial hesitations and shallow
determine their living patterns, lifestyle, risk factors and
discomfort around the its implementation are now fading
financial stability.
quickly as it begins to trust in the caliber and numerous
opportunities brought forward by Artificial Intelligence and Customers who are more regular in their financial patterns
Machine Learning.
are qualified to feel safe through low premiums. Since AI is
more capable of strict scrutiny of gathered data, it can
The only question that remains is - how far can we push its predict the amount of risk involved, protect companies from
capabilities? AI-based chatbots can be implemented to frauds and give justified insurance amount to customers.
improve the current status of claim process run by multiple MetroMile, a US-based start-up, has established such
employees. Driven by Artificial Intelligence, touchless dynamic underwriting system known as 'pay-per-mile' where
insurance claim process can remove excessive human
usage of a car determines insurance premium. Here, an AI-
intervention and can report the claim, capture damage,
based device installed on the vehicle by the company uses a
update the system and communicate with the customer all special algorithm to monitor miles, jerks, collisions and
by itself. Such effortless process will have clients filing their frictions, speed patterns and other car struggles on the
claims without much hassle for e.g. an AI-powered claims road, and it collects detailed data essential to decide
bot can review the claim, verify policy details and pass it
whether or not drivers deserve low premiums.

The process of underwriting is often
viewed as an art based on personal
judgment, but AI technologies have
also worked their way into this area of
insurance, making the process
increasingly scientific. Insurers are now
using advanced analytics and machine
learning, as well as additional sources
such as satellites and the Internet of
Things devices, to help get a more
holistic view of risk, as well as to
determine which submissions to
review in the first place. Japanese
insurance firm Fukuoka Mutual, for
instance, has been using a cognitive
machine learning based system to
scan medical records and data on
IMAGE 5- Application of Artificial Intelligence surgeries and hospital stays to

24 The Insurance Times, March 2021