This post is part of a series sponsored by AgentSync.
We recently wrote in detail about the different types of insurance fraud and how to deal with each type (for informational purposes only, of course!). Today our focus is on the other side of the coin: what the insurance industry is doing to prevent and detect insurance fraud, particularly through the use of modern technology.
A refresher on the costs of insurance fraud
Insurance fraud is not a victimless crime. It costs everyone from individuals and families to large corporations hundreds of billions of dollars every year. According to the National Association of Insurance Commissioners (NAIC) website:
“While fraud is constantly evolving and affects all types of insurance, some of the most common, measured by frequency and average cost, include the following (data sourced from The Coalition Against Insurance Fraud and Colorado State University Global):
- Life insurance: $74.7 billion;
- Medicare: $60 billion;
- Property and casualty insurance: $45 billion; The auto theft fraud totaled $7.4 billion.
- Health insurance: $36.3 billion; And
- Workers’ compensation: $34 billion ($9 billion from premium fraud; $25 billion from compensation fraud).”
Source: https://content.naic.org/cipr-topics/insurance-fraud
With so much money lost every year, it’s no surprise that insurance companies have long invested in technology to detect fraud or even stop it before it happens. Back in 2012, the Coalition Against Insurance Fraud began studying how the industry was using technology to combat fraud, publishing its findings every two years in its biennial study, The State of Insurance Fraud Technology Study.
Technology to Prevent Insurance Fraud in 2021
The latest edition of the State of Insuracne Fraud Technology Study was published in 2021. It showed that of 80 respondents (representing “the vast majority of all major insurers operating in multiple lines of insurance in the United States”), 96 percent said they use technology to detect fraudulent claims.
This number is by far the largest use case. But there was still a significant proportion of insurers using technology to detect and prevent fraud in other areas of their business, from underwriting to detecting employees engaging in internal fraud.
As we eagerly await the release of the 2023 study, which we expect to show an even greater level of technology adoption among the industry’s leading insurance carriers, we will take a closer look at how insurers are using technology in the three most commonly reported cases, to detect and prevent fraud categories across their organization (according to the 2021 study).
1. Using technology to identify fraudulent claims
Filing an insurance claim is the time when a policyholder can reap the most benefit from bad behavior, such as: B. if he overstates bodily injury or property damage or pockets payment that was intended to repair or replace the insured property. It’s no wonder that fraudulent claims are the most common form of insurance fraud. Within the fraudulent claims category, automobile claims stand out as having the highest prevalence of fraud.
For this reason, the industry has focused its efforts on using technology to detect and prevent fraudulent claims, as evidenced by the high percentage of insurers reporting this use case compared to others.
So how do they do it?
Predictive analytics: Insurance carriers collect a lot of data about their policyholders and claims and have been doing so for many years. With today’s technology, they can leverage historical data and identify patterns that indicate possible (or likely) fraud. Predictive analytics include machine learning algorithms and statistical modeling. This means the technology can sift through millions of data and flag only those cases that are likely to contain fraud. Flagged claims can include both claims that match identified patterns based on previous (confirmed) fraud cases, as well as claims with unusual activity, patterns or outliers that have not been previously observed and require review by an expert. By flagging potentially fraudulent claims, carriers devote their human attention only to the reviews they need.
Social network and behavior analysis: Actions speak louder than words, right? In today’s world, where almost everything you do leaves an electronic footprint, insurers can use technology to identify patterns of behavior that are inconsistent with a claim. The most obvious example is someone who suffers serious injuries in a car accident and seeks compensation for medical expenses and lost wages, but then goes on an expensive vacation and posts pictures of themselves diving and surfing. The person with injuries that prevent them from working is suddenly physically fit to do all sorts of things (and tweet about it!). While uncovering this type of fraud has historically relied on expensive private investigators, modern technology allows insurers to search social media and other publicly available data sources to identify cases where reality does not match a claim.
2. Using technology to detect fraudulent applications and insurance fraud
The entire insurance business is based on the premise that insurance carriers can accurately assess risk and price policies accordingly. In general, higher-risk people pay higher premiums, while pooling the risks of large populations also prevents any single person from having to bear an excessive burden. These calculations are made in the underwriting process and rely heavily on an insurance applicant providing honest information. A 40-year-old non-smoker pays less for life insurance than a 60-year-old smoker. This is based on actuarial data that determines exactly how much more risk each variable brings.
But the entire system fails when applicants provide false information on their insurance applications. Doing this to get better rates or to get insurance when someone probably wouldn’t be eligible for it in the first place is a type of insurance fraud.
How do insurance carriers use technology to detect and prevent them? In addition to the predictive analytics and social network analysis mentioned above, new technology is based on a consumer’s behavior when filling out an insurance application.
Identifying the Gaming Application: Imagine trying to get a car insurance quote online. You enter all your information, including the names and ages of all drivers, where the vehicle is stored, and the number of miles driven annually. Then the instant offer comes back and it’s way too high! So you start making adjustments: Remove a younger driver. Change the zip code where you park the car. Reduce annual miles. They constantly make adjustments and update the offer to see how your reward changes each time. This type of premium avoidance may have worked in the past, but modern technology makes it less likely to be successful. Thanks to artificial intelligence and machine learning, insurers can identify behavioral patterns that indicate someone is trying to outsmart the application. This is just one example, but across all types of insurance products, technology looks for signs that someone is adjusting application data to make a specific (and favorable) insurance decision.
3. Using technology to detect internal insurance fraud
It’s not just policyholders who are capable of defrauding an insurance carrier. Internal fraud, i.e. cases committed by insiders (e.g. insurance agents, insurance carrier employees, insurance industry executives, etc.), is also a serious and costly problem.
Some examples of internal insurance fraud include:
- An insurance agent who sells a consumer a fake policy and pockets the premium
- An insurance producer who conducts business without a valid license or with a license obtained by providing false information
- Anyone who falsifies information to a policyholder in order to induce them to cancel a policy and purchase another (usually more expensive) policy that is not in the consumer’s best interest
If you think that AI, machine learning, predictive analytics and behavioral analytics also help stop this type of fraud, you are right. In addition, insurance agencies and carriers can use:
Text mining: An employee of an insurance agent, broker or insurance carrier generates a lot of unstructured data as part of their daily work. Things like emails, video calls, notes on their desktop, or even sticky notes on their literal desktop. While the technology may not be able to sweep the contents of handwritten Post-its, it can search just about anything else. Text mining and similar practices such as opinion mining/sentiment analysis use AI to sift through massive amounts of seemingly “meaningless” communication and identify themes and patterns that may indicate fraud.
The future of insurance fraud prevention
Detecting and preventing insurance fraud is increasingly being used on a high-tech basis, but still relies largely on manual effort. According to the 2021 State of Insurance Fraud Technology Study, 39 percent of respondents said that “more than 30 percent” of cases reported as fraud came from an automated system, while the rest were entirely due to human review. Although this is an increase from 2018 data, most insurers still rely on human fraud detection in most cases. And it may not be because they don’t want to use the technology or believe that using it would be beneficial. Insurers cite their lack of IT resources and the challenge of obtaining and integrating clean data as the biggest barriers to adopting high-tech fraud prevention.
Criminals never rest, so the industry has to work hard to stay one step ahead. Currently, the NAIC Antifraud Technology (D) Working Group is preparing to present some proposed solutions at the NAIC’s annual Fall National Meeting. As a subgroup of the larger NAIC Antifraud (D) Task Force, the Technolgoy Working Group specifically aims to create a digital repository of anti-fraud plans and suggest ways for regulators, fraud investigators, law enforcement, insurance carriers and others to better share information in support of the common cause .
Speaking of connecting the industry from carriers to agencies and everyone in between… If you’re looking for a faster, easier and more secure way to manage the entire producer lifecycle – including up-to-date information about who is (or isn’t) compliant. Check out AgentSync for all states and jurisdictions.
subjects
Fraud technology
Source link
2024-02-19 05:06:16
www.insurancejournal.com
