AI & Machine Learning

3 reasons why insurers should use Natural Language Processing technology

Natural Language Processing (NLP) is a branch of Artificial Intelligence (AI) that learns from the interaction between computers and humans and uses it to read, decipher, and understand human languages. Companies can use NLP to automate communications in a way that makes sense for customers and provides them with a better user experience.

Technology firm Celent reported in April 2020, 67% of P&C insurers surveyed indicated that cost reduction and process improvement has become more important because of the COVID-19 pandemic. The insurance sector is one of many industries that suffered financial and logistical challenges due to the pandemic. NLP technologies can provide solutions that will help insurers reduce costs, save time and adapt to this new environment.

Jill Holtsinger, Vice President of Analytics and Business Intelligence at Data Axle, thinks that insurers need to hop on NLP technologies now. She says, “Natural language processing is interesting and exciting. It’s a subfield of AI concerned with the interactions between computers and human (natural) languages, particularly how to program computers to process and analyze large amounts of natural language data. By harnessing NLP, AI can successfully imitate human speech, form naturally-flowing sentences, and give human-to-machine interactions a personal touch.” Holtsinger continued, “NLP can help AI unlock unstructured data in databases and documents by mapping out essential concepts and values – allowing end-users to use that data for analytics and decision-making. Brands are using NLP to advance in the data world and provide a better UX experience for customers.”

Here are three ways insurers can use NLP to streamline operations, reduce risk and improve customer experience.

1. Fraud Detection

According to the FBI, the total cost of insurance fraud (non-health insurance) is estimated to be more than $40 billion per year. Insurance fraud affects both insurers and customers, who end up paying higher premiums to cover the cost of fraudulent claims. Insurers can use NLP to try to mitigate the high cost of fraud, lower their claims payouts and decrease premiums for their customers. NLP models can be used to analyze past fraudulent claims in order to detect claims with similar attributes and flag them.

For example, startup company Shift Technology has developed AI and NLP-based technology to help insurers detect fraudulent claims before they pay them out. Its software, FORCE, applies a variety of AI technologies, including NLP, to score each claim according to likelihood of fraud. The company recently signed a partnership with Central Insurance Companies to detect fraudulent claims in its auto and property sectors.

2. Risk Assessment

There’s no denying that weather and climate claims are up. In the U.S. alone, the average number and cost (CPI-adjusted) of billion-dollar disasters are rising. The average for the entire record (1980-2020) is 7 events per year, costing $45.7 billion per year. The average over the past five years is 16 events per year, costing just over $121 billion per year. In a time where risk assessment is more important than ever, NLP is one of the most popular tools.1 A Chartis Research survey that examined the adoption of AI methods by risk and compliance professionals, found that 37% of respondents said that NLP was either a “core component” or in “extensive use” at their organization. Many of these organizations are using ‘unstructured data,’ which NLP technologies can glean valuable insights from, without a human having to study each data point.

Consulting company, Cognizant, uses NLP to predict flood risks in the United States to better underwrite policies for their insurance clients. The tool helped its client, a global reinsurer, expand the range of data that informed its decision and reduce manual efforts by its underwriters. The results – the NLP could more accurately define risks, provided insights that lead the insurer to refine its policies and improved case acceptance rates by 25%.2

3. Speedier Customer Service

The insurance sector needs to have excellent customer service to retain their customers. Insurers have a high volume of customers who need guidance on products and help filing claims. Today’s consumers want more personalized communications as well as an immediate response to their inquiries. Hubspot’s recent research found that 90% of customers rate an “immediate” response as important or very important when they have a customer service question.3 Insurers can provide personalized, instant customer service using AI-powered chatbots or Natural Language Processing (NLP) to keep customer satisfaction high.

Insurer Allstate partnered up with Earley Information Science to develop an NLP-powered virtual assistant called ABIe. The technology was developed to help the insurer’s agents gain a deeper knowledge of their products. Since launch, ABIe has used NLP technologies to process 25k inquiries per month, providing Allstate’s clients with fast, personalized help when they need it. In addition to helping make the corporate’s agents more self-sufficient and better able to upsell and cross-sell products to their customers.

A Lexis Nexis study of insurers who are adopting AI found that most need more data and attributes than they current have in their internal databases. Among respondents representing carriers with active AI/ML implementations, pilots or approved projects, 14% are leveraging third-party solutions and 21% are combining internal and external applications. Similarly, among those starting to plan AI and ML initiatives, 12% plan to lean on third-party data, and 32% plan to use both internal and external solutions. Investing in third-party data is the best way to power sophisticated data applications, such as NLP.

Insurance is a constantly evolving industry and the pandemic forced everyone to pivot faster than ever before. Innovations in technologies such as cloud computing, identity resolution, predictive analytics, natural language processing and AI have given insurers powerful tools as they grapple with dramatically altered consumer needs, behaviors and spending patterns. Insurers who can see the opportunity in disruption, invest in new technologies and clean datasets, will set themselves and their companies up for success.

Learn more about how we help the insurance industry, or contact us with any questions.

Natasia Langfelder
Content Marketing Manager

As Content Marketing Manager, Natasia is responsible for helping strategize, produce and execute Data Axle's content. With a passion for writing and an enthusiasm for data management and technology, Natasia creates content that is designed to deliver nuggets of wisdom to help brands and individuals elevate their data governance policies. A native New Yorker, when Natasia is not at work she can be found enjoying New York’s food scene, at one of NYC’s many museums, or at one of the city’s many parks with her two teacup yorkies.