Recession Driving Insurance Fraud

By Infoglide Software CEO Mike Shultz

A recent post on McClatchy’s blog attributes growing insurance fraud to the recession:

A recent survey of 37 state insurance-fraud bureaus by the Coalition Against Insurance Fraud found that the recession “appears to have had a significant impact on the incidence of fraud” last year. On average, the bureaus reported increases in case referrals and new investigations in all 15 categories of fraud the survey covers.

The two largest sources of fraud listed in the CAIF study are phantom vehicle accident and staged accidents. In staged accidents, perpetrators of these crimes tend to be involved in multiple incidents. They create and leave a trail of information that remains captured in insurance company datasets. Unfortunately, many of these companies don’t take advantage of sophisticated tools that can find the crooks.

Let’s look at the example of staged vehicle crimes and how they can be stopped. A ring of people who successfully pull off a staged accident and are subsequently reimbursed by insurance companies usually decide to repeat their success. Since they fear being caught, each person takes different roles, changing his/her name and address slightly to avoid being caught by the data matching algorithms employed by insurance companies in the claims process. One person acting as driver in one staged accident plays the role of witness in the next accident and the passenger in the third. Each time an accident is reported, that person changes attributes of their identity, like name and address, to trip up existing software systems.

The state of entity resolution technology has been advancing rapidly. What used to be undetectable using “data matching” software can now be easily found using entity resolution. We’ve written before about the difference between simple data matching and entity resolution and how entity resolution enables hidden relationships to be uncovered.

Working with ambiguous data is a challenge, and it can overpower traditional data matching and fuzzy matching techniques. Entity resolution disambiguates insurance fraud data to find the hidden relationships between participants in fraud rings, allowing them to be stopped and prosecuted