Machine Learning Times
Machine Learning Times
PAW Preview Video: Evan Wimpey, Director of Strategic Analytics at Elder Research
 In anticipation of his upcoming presentation at Deep Learning...
Podcast: P-Hacking—How to Know Your Predictive Discovery is Conclusive
  Welcome to the next episode of The Machine Learning...
PAW Preview Video: Piotr Wygocki, Ph.D., CEO & Co-Founder at MIM Solutions
 In anticipation of his upcoming presentation at Predictive Analytics...
PAW Preview Video: James Taylor, Decision Management Solutions
 In anticipation of his upcoming presentation at Predictive Analytics...

7 years ago
Big Data Is Making a Splash in the Insurance Industry


There’s conflicting opinions on when the term Big Data really came onto the scene, but it is undeniable that its notoriety has skyrocketed in the past few years. Big Data has become the hot topic buzzword around the internet, as is made obvious in the Google Trends graph below.

One by one as analytics solutions became more accessible, industries found different ways to leverage the Big Data Revolution to their best advantage in their field. Virtually every industry, from manufacturing and retail to healthcare and education, has found a use for the ever-growing labyrinth of data resources.

PATimes AD
Use Code PATIMES15 for 15% off a two day pass or combo pass. (Excludes workshops & All Access)

The Insurance Industry is no exception in the Big Data Revolution. The Ernst and Young 2015 Global Insurance Outlook claims “technology” is the one word that encompasses the Insurance industry right now. The report states, “Insurers across all regions are capitalizing on data analytics, cloud computing, and modeling techniques to sharpen their market segmentation strategies, reduce claims fraud and strengthen underwriting and risk management.”

big data trending

Although there are many ways that Insurers are utilizing Big Data and data analytics to benefit their bottom line, there are 5 areas being impacted the most.

1. Data for streamlined underwriting

Insurance underwriters are faced with the daily challenge of providing policy recommendations that are both fair to the consumer, as well as protect the best interest of the insurance company. Big Data is changing the future for underwriters as they must adapt to their new roles as data analysts as well as underwriters.

A study by Marketforce, the Chartered Insurance Institute (CII) and the Chartered Institute of Loss Adjusters in conjunction with Ordnance found that most underwriters are taking the evolution of their industry in stride. The study revealed that 9 out of 10 underwriters see the potential in access to real-time claims data to improve pricing accuracy.  Real-time data mining is streamlining the underwriting process by providing accurate, current insights that could have taken days to locate and consolidate. With access to quality data sources, underwriters are able to complete processes in less time and with better accuracy. Real-time data facilitates streamlined processes leading to higher placement rates and a much faster underwriting cycle.


2. Data for Personalized Policies

Access to multichannel data sources gives underwriters the ability to base premium costs and policy parameters on a more realistic view of risk as opposed to generalized assumptions based on factors such as location and age. Consequently, this integration of highly granular and individualized characteristics into the underwriting cycle is driving a more personalized consumer experience. Customers who feel they are receiving fair treatment instead of at the mercy of generalizations receive a more positive experience and are more inclined to remain loyal clients.

3. Identifying Customers at Risk of Cancellation  

Leveraging Big Data insights is well known for its ability to provide quality prospects for businesses, but another lesser known feature is its ability to shed light on low quality prospects or frustrated clients. Advanced analytics tools allow insurers to target individuals who are apt to be a long term loyal customer, and also to weed out individuals who are a high risk of canceling coverage. Predictive analytics is used to track and reveal signal behaviors that indicate an impending cancellation. This allows insurance agents to reach out to unhappy consumers before their final decision has been made, and tailor opportunities to encourage them to stay with the company.

4. Identifying Risk of Fraud

Fraudulent claims are an unfortunately common occurrence afflicting the insurance industry. The Coalition of Insurance Fraud estimates that nearly $80 billion in fraudulent claims are made annually in the United States. This staggering statistic has led to heightened awareness and the use of predictive data analytics to detect applicants with a higher propensity to commit fraud. Additionally, after a claim has been made Insurers can use data mining to track digital and social channels for evidence of fraudulent behavior.

This excerpt is from Smart Data Collective. To view the whole article click here.

Larisa Bedgood, Director of Marketing, DataMentors
Originally published at

Leave a Reply