Identity Resolution Daily

By Doug Wood - Infoglide SVP of Sales

Government and commercial organizations are under increasing pressure to more effectively identify and unravel threats before they happen.  Predictive analytics tools have traditionally been deployed in hopes of isolating transactional behaviors that may point to a risk of loss.  The market is well served with these systems, yet institutional fraud seems more prevalent than ever.  Lumping in good customers with bad ones simply because they coincidentally perform similar types of transactions?  Not smart.

As a result, organizations are turning to identity resolution technology that drills down into the entities and associated relationships with a high degree of confidence.  In essence, technology that points to ‘who’ instead of simply ‘what’.  Identity resolution engines help organizations transfer from a pattern-centric to an entity-centric fraud analytic model.

So, how can analysts reconcile the massive amount of related data that exists in bits and pieces across dozens or hundreds of disparate databases?  How can they ‘connect the digital dots’ between individuals and other entities represented across so many data sources?  Key to understanding identities is the ability to perform social link discovery to determine not just ‘who’s who’… but also ‘who knows whom’.

Data warehouses and data mining tools have been used in the past to try and solve this challenge; however they require the data to be aggregated, standardized or otherwise deteriorated in order to be mined.  That’s like a CSI investigator tidying up the crime scene ahead of time, so she can more easily look for evidence.  Infoglide Software Corporation’s Identity Resolution Engine™ (IRE) looks at the evidence in all its’ gore and imperfections to present the analyst with a clear and concise view of the individuals who would commit fraud.

Gartner Group – in their 2009 Hype Cycle for Master Data Management report – suggested that “entity resolution and analysis was previously an obscure technology that has come to the forefront as a result of world events and market forces where it is used to identify identities and networks of identities who are attempting to hide their relationships to each other.”

Scott Schumacher, a government security and technology expert and former chief scientist at Initiate Systems (now IBM’s InfoSphere Identity Insight), may put it best when he writes “By identifying and managing relationships between persons of interest and other individuals or objects, (id)entity resolution delivers a more comprehensive view of people, places or things and their activity.”

By significantly mitigating the signal-to-noise challenge faced by fraud and crime analysts, organizations can be more proactive in identifying and preventing unwanted behaviors.  That’s precisely what an identity resolution engine does.

Share This

By Doug Wood - Infoglide SVP of Sales

The word ‘triage’ tends to bring to mind the settings of a hospital emergency room.  Doctors and nurses try to examine the patient data quickly to ensure that patients with the most urgent needs are treated first.  This same concept holds true for insurance. Understanding which claims need further examination is a daily struggle that most P&C insurers deal with.

The Federal Bureau of Investigation estimates that the total cost of insurance fraud (excluding health care) exceeds $40 billion per year. That means insurance fraud costs the average U.S. family between $400 and $700 annually in the form of increased premiums.  Some call this the ‘fraud tax’.

A central component of a successful claim triage program is the ability to quickly and correctly identify a suspicious claim. These technologies trigger alerts when claims fall outside of normal patterns. The market is well served with competing technologies that provide rules-based predictive and behavioral analytics.

 With predictive analytics, fraudulent claims tend to slip through the cracks if the fraudster is careful not to trigger an alert by doing anything that would look suspicious.  Fraud is a chameleon, after all, and it thrives when allowed to blend into the background patterns.

A key new tool has emerged over the past few years which allows insurers to focus on the ‘who’ as much as the ‘what’. Identity resolution engines look at all of the attributes of the people, places and things involved in a claim and compare them to the goldmine of data already sitting behind the insurer’s firewall.  Accounting for variations in names, addresses, dates and a host of other attributes, identity resolution engines look at possible identity matches across data silos, while simultaneously discovering hidden social links between individuals.  For example, does the witness in Claim A share an address with someone currently being investigated by SIU in Claim B?  Do they have similar names or phone numbers?  Is there a fraud ring at work here?

Exposing suspicious claims based upon this robust analysis of the people involved is a sure-fire way to expose the chameleon and reduce fraud costs dramatically.

Share This