Technology permeates every aspect of our lives, from the way webuy our goods to how we monitor our kids and homes, and it is alsohaving a tremendous effect on the insurance industry.

The Washington, D.C.-based CoalitionAgainst Insurance Fraud says that insurance fraud is an $80billion-dollar-a-year enterprise, and as fraudsters become moredaring, investigators are using a broad range of tools to capturethem:

• Data analytics or rule-based analytics allowcompanies to look at large amounts of data and ask some commonquestions to help flag claims that require a bit moreinvestigation. For example, in a health insurance claim, if aprocedure that could only be performed on a female was submitted asa claim on a male, this would trigger a flag indicating that theclaim requires a closer examination.

• In fraud modeling, predictive analytics looksat fraud based on a series of different risk factors and helpsinsurers predict which claims are most likely to have some sort offraud issue, explained Dan Zitting, chief product officer forACL, a softwarecompany and fraud auditor based in Vancouver, British Columbia."We're basically building a statistical model that says these arethe claims we should investigate."

• Through network analysis, insurers can look atthe relationships between people such as family and co-workers, anddifferent elements in the data to identify potential fraud. Casemanagement can help investigators who are looking for anomaliesbased on these types of analyses determine whether there really isfraud involved or if the analysis has just indicated a falsepositive.

The effectiveness of a successful data analytics program restson several things. "One of the biggest determining factors dependson how much support the company has from their IT department, howmuch data they have and how much experience they have in fraudanalytics," said Zitting. "In any company, just the basics worklike looking for which claims were paid out twice or who is usingthe social security numbers of dead people. It's easy to get thesequick wins and low-hanging fruit before going to more complexmodels."

Zitting said that a lot of companies know fraud exits, but don'tnecessarily choose to pursue it. He estimates that 5-8 percent ofclaims paid are fraudulent and says that fraud exists in everycompany regardless of size.

Evolving technology

While data analysis has been available for close to 30 years,the technology continues to evolve as data analysis applicationsare built. These pre-built and pre-configured apps allow insurersto use them without a lot of modifications.

"You don't have to figure out how to build a complex analysisfor some of these questions," said Zitting. "There are more out ofthe box apps to help investigators narrow down information frommillions of claims to a manageable population of claims to look atand work from. That way they can spend more time on meaningfulclaims."

Zitting said an explosion of data sources such as social media,information in the public domain and from the government helps tomake the analysis much richer and provides a broader picture of aclaim.

As technology evolves, however, fraudsters are also stepping uptheir efforts. "We're seeing more areas of cyber fraud emerge andthey are getting very sophisticated in using these techniques,"added Zitting. "They are using data analysis to identify whatpatterns banks are using to identify fraudulent purchases andasking, 'What shouldn't I do so I don't get their attention?'"

Analytics are getting more advanced as well. Zitting describedthe new trend of using text mining to identify sentiment or naturallanguage that could point to fraud. "Text analysis was used toidentify collusion between insureds and their agents. Insurers areusing text analysis on the bodies of emails to identify patterns ofspeech that are indicative of fraudulent relationships."

He said that this type of analysis was used in eight major caseswhere the companies knew there had been fraud involving theiragents. When they compared the speech patterns in the emails to thelanguage from the rest of the company population, it enabled thecompanies to look at the agents involved more closely based ontheir speech patterns. Some of the wording included instructionsfrom the agents to the fraudsters such as, "Submit the claimafter…" The companies also found that there was a high correlationto the volume of communication in terms of the amount of text andemails between the parties involved.

Fraud trends on the rise

Investigators and insurers are also seeing an increase in anumber of fraud-related trends. Zitting said that ransomware, wherea fraudster takes control of a computer system or database andholds it for ransom, is becoming very problematic. This yearseveral hospital databases were held for ransom, which isfrequently requested in bitcoins, a digital form of payment that isuntraceable.

In addition, Zitting said that whenever there is substantialregulatory change, it seems to foster new frauds. He cited theAffordable Care Act and the changes in regulation it produced. "Itcreates new opportunities for fraud, new insureds, new risks notpreviously investigated and new fraud schemes arise around thoseregulatory changes," he said.

When it comes to fraud, everything seems to be related toidentity, whether it is impersonating people, getting theirpasswords, using their identities to steal information, orperpetrating some type of internal fraud within a company. "When aperson's behavior changes in our systems, that could be anindication of fraud," he explained.

Another trend Zitting cautioned against involves a rise ininternational terrorism, since money laundering activitiesfrequently involve fraud. "This is an area regulatory bodies needto be watching," he added.

With cars becoming more automated and their "black boxes"collecting more information, this is providing valuable data forinsurers, but Zitting says the questions will be "What do we dowith it and how do we protect it?" as hackers seek ways to captureand use this information.

Technology will continue to evolve, creating new opportunitiesfor insurers to gather more information, provide better products,and monitor claims for fraud. However, fraudsters will continue tofind even more creative ways to capture this information and use itfor their own endeavors.