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

Share This

McClatchy: Recession is fueling a boom in insurance fraud

“Whether it’s worthless health plans peddled by fax, staged auto accidents, arson or slip-and-fall accidents at the local mall, insurance fraud of all kinds is booming in the recession and consumers are paying the price in higher premiums.

SC Magazine: Technology solutions can be the resolution to terrorist threats

“Poulter said that when it comes to areas such as fraud detection and anti-money laundering (AML), identity resolution technology can assist financial institutions in combating identity fraud and leverage name matching of hidden patterns and correlations to prevent attempts to disguise identity. A single view of this information plays its part in the fight against terror, giving authorities a greater ability to prevent money laundering, which may lead to the funding of terrorist campaigns.”

Computerworld: Cloud Computing Will Cause Three IT Revolutions

“Over the next two to five years, expect to see enormous conflict about the technical pros and cons of cloud computing that will, at bottom, be motivated by the perception on the part of the participants as to whether cloud computing represents a benefit to be embraced or a threat to be resisted. In particular, cloud computing’s three characteristics — the illusion of infinite scalability, lack of a long-term commitment, and pay-by-the-use — will result in three revolutions in the way IT is performed, and each of the revolutions will have its adherents and detractors.”

Initiate blog: An Economic Business Case for Entity Resolution

“Restated, intelligence information sharing, analysis and proactive action (such as that performed by Interpol) are the most efficient way to economically battle terrorism. Interpol’s mission is to coordinate information and operations among nations, to allow countries to track criminals across borders and share information of common interest. This also happens to be a very good way to describe the business function of entity resolution technology.”

Share This

“In the last post we examined how entity resolution (ER) systems are actually implemented, starting with the most basic merge/purge process and heterogeneous join systems. Both of these approaches focus on collecting equivalent references from among the sources provided, either as a large batch of references in a single file, or through queries against a federation of databases…”

The Foundry: Thwarting the Next Terrorist Attack: Are We More Prepared?

“Knowing what we know now, would the U.S. be able to stop another attack like that of Christmas Day 2009? This is certainly the question on the minds of many Americans today.  It is also one that Jamie McIntyre, veteran journalist and blogger for Military.com, had the opportunity to ask of Rand Beers, Under Secretary for National Protection and Programs Directorate from DHS, at a Heritage Foundation National Security Bloggers Luncheon.”

http://www.youtube.com/watch?v=ub8K6ApOnGE

Perceptive Information Strategies: Informatica and the Identity Opportunity

“In the middle of all of this are software providers, primarily IBM InfoSphere Identity Insight Solutions, Infoglide (which is providing software for the DHS) and Informatica… Identity recognition and resolution systems enable organizations to use data matches to gain a better understanding of identity across multiple systems. This could include not just individual identities but also networks and relationships: that is, who people know and how they are connected.”

Managing Automation: The MDM Supplier Market Gets a Little Smaller

“It’s been a heady couple of months in the IT infrastructure market, as any independent company that wasn’t tied down seemed to be swept up in a whirlwind of M&A activity. Independent data integration specialist Informatica, a 4,000-customer company in business since 1993, announced in January that it had acquired Siperian for $130 million.”

Share This

In the last post we examined how entity resolution (ER) systems are actually implemented, starting with the most basic merge/purge process and heterogeneous join systems. Both of these approaches focus on collecting equivalent references from among the sources provided, either as a large batch of references in a single file, or through queries against a federation of databases.  The entity identities found by these ER systems are transient in the sense that they depend upon the sources input into the process.  When different sources are provided, different identities will emerge.

On the other hand, there are ER systems that retain and manage identity information.  By doing this they are able to “recognize” the same identity over time and assign that identity the same entity identifier (sometimes called “persistent identifiers” or “persistent links”).  In Customer Data Integration (CDI) applications, these kinds of systems are sometimes called Customer Recognition Systems.

Two major types of ER systems perform identity management.  The first type is the “identity resolution” system.  It is most effective in situations where a fairly stable set of known identities of interest exists, such as the set of vendors or customers of a company, a set of products, or the students enrolled in a school.  The attributes of these identities are pre-loaded into the system and assigned identifiers.  When a reference is given to the system, it then decides whether the reference is to one of the known identities, and if so, returns the identifier of that identity.

Identity resolution systems can operate in either batch or transactional mode.  In cases where there are a large number of pre-stored identities, the performance of batch operations can be improved through distributed processing where the identities are partitioned over multiple processors and resolved in parallel.

However, there are many situations where the identities are not necessarily known in advance, or in some cases  the entities are known but simply not organized in such a way that they can be easily pre-loaded.  For example, suppose two companies merge and each company has its own customer database. The customers are identified in different ways in each database, and furthermore, for the customers of one company, poor systems and practices prevent having any confidence that the master records are unduplicated across business lines or company locations.

The type of system often applied in these situations is an “identity capture” system.  The identity capture architecture can be seen as a hybrid of  merge/purge and identity resolution systems.  It supports identity management and persistent identifiers, but without starting with a preloaded set of identities.  In my next post, we’ll delve deeper into the identity capture process.

Share This

tdwi: Informatica Ups the MDM Stakes

“Until now, Informatica’s MDM strategy has largely been peripheral. It had most of the tools (e.g., data integration, data quality, data profiling, and identity resolution) but tended to partner with bigger or best-of-breed players to promote MDM-oriented offerings or services… What’s risky about the acquisition of Siperian is that it imperils Informatica’s existing MDM partnerships (especially with Oracle Corp.) and compromises its neutrality pitch.”

GCN: Fusion centers to be assessed

“Fusion centers will conduct self-assessments, followed by a gap analysis and peer reviews, according to officials at the National Fusion Center Association, a new not-for-profit organization based in Alexandria, Va., that represents the 72 fusion centers. The assessments are meant to determine their progress in reaching baseline capabilities. Those capabilities were created by a federal advisory committee that also wrote the original guidelines for those centers.”

WorkersCompensation.com: NYSIF Announces 154 Arrests

“Recent significant cases resulting in millions of dollars in savings to NYSIF have included claimants who receive benefits while operating businesses or remain employed in other capacities, the most prevalent type of workers’ comp. fraud. Other cases involve premium fraud, the most costly type, in construction, asbestos abatement and other contracting, including investigations in conjunction with the U.S. Department of Labor, the U.S. Postal Inspector, and local labor racketeering bureaus. Still other cases involve fraudulent provider billing.”

SignalScape: Experts Ponder Both Sides of Border Security

“The DHS has also tested mobile identification systems and created an information sharing plan with the Department of Justice which allows officials to search for criminal records. Art Macius, chief of staff at the Transportation Security Administration (TSA) added that organizations such as his and the DHS must also share information with their international counterparts. This international cooperation includes efforts such as cargo screening for commercial aircraft though efforts such as the Secure Flight program. Macius said that by this spring, the program will work with U.S. airlines to screen baggage and air cargo, and that the coverage will extend to international carriers by the end of the year.”

Share This

“Andrew White of Gartner recently posed a question about whether master data management (MDM) is dead. He didn’t actually suggest that the demise of master data management is imminent. He was challenging whether our current terminology adequately clarifies the current reality about MDM and associated product areas.”

Inside the Biz: The Good News about MDM Market Consolidation

[Jill Dyche] “Last year, Informatica’s MDM story verged on the schizophrenic as the company simultaneously advocated a “roll your own” approach to MDM using various software components while at the same time making investments in both Siperian and rival Initiate Systems. Siperian fills in some significant voids in Informatica’s MDM capabilities, most notably hierarchy management and transaction integration—updating the golden record in real time.”

porter: FAQ Secure Flight

“What is Secure Flight and what does it do? Secure Flight is a behind the scenes program that streamlines the watch list matching process. It will improve the travel experience for all passengers, including those who have been misidentified in the past.”

Computerworld: Meeting an Olympic-size security challenge

“First is the classic ‘entity resolution‘ challenge. Information about any individual is likely going to be scattered across a range of databases. While one database may contain a red-flag item — a pending drug charge or a secondary connection to a known terrorist — another database may not. The challenge is bringing this information together to create a single record — a ’single version of the truth’ — about an individual or entity.”

Share This

Andrew White of Gartner recently posed a question about whether master data management (MDM) is dead. He didn’t actually suggest that the demise of master data management is imminent. He was challenging whether our current terminology adequately clarifies the current reality about MDM and associated product areas.

Certainly the terms describing many markets and types of products are being associated with MDM. Jackie Roberts of DATAForge pointed out that the definition of MDM now seems to include “data integrity, data quality, entity resolution, matching, data integration, governance, metrics and analysis.”

While entity resolution was mentioned in her list, our obsessive focus on entity resolution (aka identity resolution) leads to the conclusion that, rather than being subsumed, its role is growing. Wayne Eckerson at TDWI seems to agree that identity resolution is a critical component of the recent MDM acquisitions. In his post about the acquisitions by Informatica and IBM of Siperian and Initiate Systems, respectively, he described the two transactions this way:

“You could say that Siperian is mostly MDM, but with identity resolution and other capabilities, whereas Initiate is mostly about identity resolution, but with MDM and other capabilities.”

Identity resolution is becoming an integral part of many product areas. Within MDM itself, creating a single-entity view is best done with an identity resolution engine. Data mining is greatly enhanced by the addition of entity resolution. Dan Power of Hub Solution Designs wrote about how key identity resolution is to data matching. We’ve talked about how social CRM can resolve identities of individuals across multiple disparate data sources using identity resolution, as well as “rationalize multiple variations and errors and anomalies that block finding existing customers within their systems”.

Although identity resolution technology has been years in the making, it has only recently risen into the consciousness of most analysts and customers. Because of its ability to bring enhanced clarity to ambiguous data, advanced identity resolution is now beginning to have a significant impact across many data-centered disciplines.

Share This

IT-Director.com: The Informatica Event

[Philip Howard] “To begin with, the company talked about its acquisition of Siperian. I have already commented on this but one point that emerged at the conference was the way that Informatica describes Siperian as infrastructure MDM as opposed to application MDM. This is a hitherto unrecognised distinction (with respect to terminology) in the MDM market. Informatica distinguishes the former from the latter by saying that infrastructure MDM is domain and data model independent.”

Workforce Management: Medical Clinic Owners Plead No Contest to $60 Million Workers’ Compensation Fraud

“Investigators alleged that the pair purchased thousands of workers’ compensation client referrals from an attorney television advertising service. Clients were then sent to doctors who had a relationship with Premier, which would handle billing and collection work in return for a 50 percent fee for money they collected. Clients were then sent to attorneys who had a business relationship with Fish and Bacino, investigators allege. ‘Getting kickbacks for referring medical payments is illegal and drives up the costs in the system,’ California Insurance Commissioner Steve Poizner said in a statement.”

SignalScape: DC Police Chief Cathy Lanier Describes How Technology Is Changing Police Work in the Capitol

“The MPD also established a fusion center, which is responsible for the national capitol region. From a homeland security perspective, Chief Lanier said that the center collects and stores crime and terror alerts into a data warehouse.”

Injured Workers’ Law Firm Blog: Insurance Fraud Is a Huge Crime

“The fraudulent claims that can be made through insurance companies are categorized as being soft or hard. Soft fraud is the most common type of fraud and usually takes place when someone exaggerates a claim being made. Hard fraud takes place when someone deliberately plans a deceptive act such as a collision or the theft of their vehicle.”

Share This

“In March 2006, the Communications Fraud Control Association (CFCA) estimated that annual global fraud losses in the telecom sector were between $54 billion and $60 billion, and the losses continue to be substantial. Many types of fraud have been identified, but by far the most prevalent is subscription fraud.”

ITBusinessEdge: Analyst: SAP Missed Out During Recent MDM Acquisition Spree

“SAP, on the other hand, has had a lot of issues in the past couple of years. They haven’t made a direct MDM acquisition since they acquired A2i years and years ago, which was a PIM vendor and they’ve just been working off of that architecture and been trying to improve it.”

Liliendahl On Data Quality: Data Quality Tools Revealed

“Data matching is the ability to compare records that are not exactly the same but are so similar that we may conclude, that they represent the same real world object.”

BeyeNETWORK: Master Data Management: Moving Forward…

“So now that MDM has been around for a while, and the master data terminology has drifted into our standard vocabulary, it might be worth stepping back and asking a different question:  Is MDM the revolutionary approach to organizational data consolidation and enterprise information management or is it devolving into yet another  (of many) data management tools?”

Share This

In March 2006, the Communications Fraud Control Association (CFCA) estimated that annual global fraud losses in the telecom sector were between $54 billion and $60 billion, and the losses continue to be substantial. Many types of fraud have been identified, but by far the most prevalent is subscription fraud.

A new subscriber signs up for mobile service using false or stolen identification, with no intention of paying the bill. Since new subscribers are given a grace period of one to three months before the account is shut off, the criminal can make thousands of dollars worth of calls before being detected.

Subscription fraud can be difficult to differentiate from simple bad debt when genuine customers are unable to pay. It’s been estimated that 30% or more of all bad debt is actually subscription fraud.

Different solutions have been tried yet fraud continues to be a problem. One common method is to look for patterns of use that suggest potential fraud, but criminals adapt and learn to probe the limits of these fraud detection systems fairly quickly.

Given the industry’s long history with fraudsters, it seems probable that enough is known about them that they could be spotted at the time they subscribe.  Using similarity searching technology, would-be fraudsters can be vetted against lists of known bad actors. Using multiple public and private data sources, non-obvious relationships can highlight risky individuals, and they can then be asked to submit to a more thorough qualification process.

Identity resolution is already used across multiple industries to solve similar problems. By matching an individual’s attributes with common attributes associated with those committing fraud, the “bad guys” are being detected in areas like lottery fraud, fusion centers, insider trading, and workers’ compensation employer fraud. Part of finding the bad guys is finding hidden relationships, connections that often uncover rings of criminals.

The “birds of a feather” axiom predicts that subscription fraud criminals often share the same types of social networks. Applying identity resolution to subscription fraud problem may be the way to finally solve it.

Share This