Tag Archives: fraud analytics

Financial Crimes, Investigation Software, Link Analysis

Part 2: Investigating the Investigations – X Marks the Spot

Leave a comment

Posted by Douglas Wood, Editor.  http://www.linkedin.com/in/dougwood
Part One of this series is HERE.
Most of the financial crimes investigators I know live in a world where they dream of moving things from their Inbox to their Outbox. Oh, like everyone else, they also dream about winning the lottery, flying without wings, and being naked in public. But in terms of the important roles they perform within both public and private sectors, there is simply Investigating (Inbox) and Adjudication (Outbox). Getting there requires a unique blend of their own capabilities, the availability of data, and the technology that allows them to operate. In the diagram below, ‘X‘ marks the spot where crimes are moved from the Inbox to the Outbox. Without any of those three components, an investigation becomes exponentially more difficult to conclude.
Presentation1
In part one of this article two weeks ago, I wrote about the Investigation Management & Adjudication (IMA) side of financial crimes investigations. I coined that term to call out what is arguably the most integral component of any enterprise fraud management (EFM) ecosystem. The original EFM overview is here.

   “The job is almost unrecognizable to those who once used rotary phones in smoke filled offices…

Twenty years ago, IMA was based primarily upon human eyes. Yes, there were technology tools available such as Wordperfect charts and Lotus 1-2-3 spreadsheets, but ultimately it was the investigator who was tasked with finding interesting connections across an array of data elements including handwritten briefs, telephone bills, lists of suspect information, and discussions with other investigators. The job got done, though. Things moved from the Inbox to the Outbox, arrests were made and prosecutions were successful. Kudos, therefore, to all of the investigators who worked in this environment.
Fast forward to today, and the investigator’s world is dramatically different. The job is the same, of course, but the tools and mass availability of data has made the job almost unrecognizable to those who once used rotary phones in smoke filled offices. Organizations began building enterprise data warehouses designed to provide a single version of the truth. Identity Resolution technology was implemented to help investigators recognize similarities between entities in that data warehouse. And today, powerful new IMA tools are allowing easy ingestion of that data, improved methods for securely sharing across jurisdictions, automated link discovery, non-obvious relationship detection, and interactive visualization tools, and -importantly – packaged e-briefs which can be understood and used by law enforcement, prosecutors, or adjudication experts.

     “Without any of these components, everything risks falling to the outhouse…

With all these new technologies, surely the job of the Investigator is becoming easier? Not so fast.
IMA tools – and other EFM tools – do nothing by themselves. The data – big data – does nothing by itself. It just sits there. The best investigators – without tools or data – are rendered impotent.  Only the combination of skilled, trained investigators using the best IMA tools to analyze the most useful data available results in moving things from the Inbox to the Outbox. Without any of these components… everything eventually risks falling to the Outhouse.
Kudos again, Mr. and Mrs. Investigator. You’ll always be at the heart of every investigation. Here’s hoping you solve for X every day.

Investigation Software, Major Case Management

Investigating the Investigations.

Leave a comment

Posted by Douglas Wood, Editor.
A few years ago, I read a book called Fraud Analytics by Delena Spann.  Ms. Spann is with the U.S. Secret Service, Electronic & Financial Crimes Task Force. The book is an overview of investigation analytics with specific information about some former technology leaders in this area.
The IBM i2 toolset is discussed, along with offerings from Raytheon, Centrifuge, and SAS, and FMS’ Link Analytics, and others. (My friend Chris Westphal, formerly of Raytheon Visual Analytics, by the way, published his book ‘Data Mining for Intelligence, Fraud & Criminal Detection’ a few years ago and is another one I strongly recommend.)
Both books offer advice and use cases on how technology can be applied in the fight against crime. A few months ago, I summarized the types of technology being put to use as tools to prevent, detect, and investigate fraud and other criminal activities. (It’s worth a quick read.) What I’m investigating today, however, is… well, investigations.

“IMA is the most critical connection between technology and investigators.”

In my technology summary, I termed this area Investigation Management & Adjudication (IMA). IMA is the most critical connection between technology and humans within an enterprise fraud management ecosystem. Incorporating key elements of enterprise case management, collaboration, link visualization, information dissemination and knowledge discovery, this layer of functionality is designed to uncover insights which aid in investigating complex incidents. The result ought to be actionable visualization of critical entities, and documented results for potential litigation and regulatory compliance.
IBM i2 has long been considered a thought and market leader in this segment – deservedly or not. Palantir Technologies plays in this area as well. Perhaps no company is more in tune with this market, though, than Visallo with their leading investigation analytics platform. Each platform clearly adds value to investigation case management solutions by providing powerful, emerging functionalities that allow easy and intuitive consumption of data in any form. For investigators, the more data – and the easier that data is to consume – the better.

“Users want actionable intelligence, not endless queries.”

What makes for good IMA? A few things, actually. First among them is the technology’s ability to adapt to the way human beings think and act. Users want actionable intelligence, not endless queries. IMA tools, therefore, ought to interact with the investigator in a consultative way that a fellow investigator would. “Hey, have you thought about this, Mr. Investigator?” and “Maybe you should look at that.”
Second, IMA ought to have context. Technologies that simply point to two entities and say, ‘Hey these things look linked‘ are great but leave all of the thinking up to Mr. Investigator. The IMA tools that I like have contextual values associated to those links. ‘Hey, these things look linked AND here’s why that’s important’. Big difference.
Third, IMA should bring the investigations to closure. There are a lot of data mining tools out there that allow querying with case management. How, though, does the investigator get to the point where an investigation is solved and prosecutable? Once again, the most functional IMA products act the way humans do. They package up the results of the investigation in an easy-to-comprehend document that can be shared internally or with police. No loose ends.

“Every investigation ends with an investigator.”

Predictive analytics, big data, and real-time alert scoring are the current industry buzzwords. They should be. They’re important. At the end of the day, however, every investigation ends with an investigator. Putting the right tools in their hands is often the difference between success and failure in an entire enterprise investigation system.
That’s precisely what Crime Tech Solutions, LLC does. Please take a moment to look us over.
Part Two of this series is now available HERE.

Financial Crimes, Link Analysis

SEC taking stock of analytics (and a cool use case for stock exchanges)

Leave a comment

Image Posted by Douglas Wood, Editor.
I read with interest today an article about the SEC’s use of analytics in the ongoing fight against financial crimes. The link to that article is below. It reminded me of some work I once did with a major stock exchange around insider trading.
As a passionate anti-fraud technologist, I was thrilled with the challenge of helping the stock exchange better recognize cases of illegal insider trading. The results of the work we did was pretty cool.
The stock exchange – as do all exchanges – had a great deal of data at their disposal. They knew, for example, the names of each and every ‘insider’ within every company listed on their exchange. Insiders include senior executives, board members, legal counsel, auditors, and so on.  Basically, everyone who knew – or ought to have known – about an upcoming event that would likely cause a significant change in stock price.
They also knew, of course, the identity of investors who traded profitably prior to the public release of that information. The problem was exposing the hidden relationships that might exist between Insiders and investors.
Here is an actual example… Joe Blow was an associate partner at the independent accounting firm responsible for auditing the quarterly financial results of publicly traded Company A. By definition, Joe is an insider. He knows Company A’s financials. Jane Doe dumped her entire position in Company A mere days ahead of what turned out to be very poor results. The stock plummeted, and Jane was saved from significant losses.  She was seemingly a complete outsider. So, did she somehow know Joe Blow (or any other insider)? Or was she just one lucky gal.
Using link analysis, crime mapping, and behavioral analytics, we set about the challenge of finding out. Here’s what the analytics exposed:
Joe Blow, the insider by way of being employed at Company A’s auditing firm, shared an address with… oh, let’s call him “Rich Quick”. Rich held no positions with Company A whatsoever.  He did, however, own a pet food store with a lovely young lady.  Can you guess her name?  Yep.. Jane Doe. So, the analytics exposed that Company A had an insider relationship with Joe Blow. Joe lived with Rich Quick. Rich owned a business with Jane Doe. Coincidence? Not likely.
Without the ability to draw out hidden links between individuals and organizations, this case may never have been discovered.  It’s like Six Degrees of Kevin Bacon, only with much higher stakes. All of the suspects were investigated and prosecuted.
(Note: All the names in this example are fictitious, but the case is not. If your name happens to be Jane Doe, Joe Blow, Rich Quick… or if you work for an organization called Company A, rest assured that I’m not talking about you.)
Here is the link to the SEC article.  http://fcw.com/articles/2013/09/18/sec-taps-analytics-to-predict-risk.aspx?s=fcwdaily_190913 .

Investigation Software, Major Case Management

Financial Crimes and Technology

Leave a comment

Posted by Douglas Wood, Editor. 

In the midst of preparing for a presentation last week, I entered the term “financial crimes” into my internet search engine. I’ve probably done this same search a hundred times, but seemingly never took notice of the staggering number of results. Over two million of them!

Among those results are a stunning number of definitions, news reports, and general articles. But with so many links to seemingly unconnected terms such as check fraud, credit card fraud, medical fraud, insider trading, bank fraud, health care fraud, tax evasion, bribery, identity theft, counterfeiting, and money laundering – it must appear to the uninitiated that an understanding of ‘financial crimes’ requires an Einstein-like intelligence pedigree.

To those involved in the daily prevention / detection / and investigation of financial crimes, however, the term can be effectively boiled down to:

1) Intentional deception made for personal gain, and

2) The illegal process of concealing the source of those gains.

Everything else – all that other noise – simply falls underneath that definition, and only a cohesive combination of human intelligence and technology can take a bite out of those crimes.

Of course, most companies that are targets of these crimes invest heavily in different forms of technology for enterprise fraud management and anti-money laundering systems.  There are dozens of vendors in this market with varying levels of functionality and service offerings.

The problem with too many of those offerings, however, is that they do not account for organizational truths such as functional  (and data) silos, data quality issues, changing criminal tactics, human limitations, and big data.

A complete enterprise solution for financial crimes management must include automated processes for:

Customer Onboarding – Knowing the customer is the first step an organization can take to prevent financial crimes. A holistic view of an entity – customers, partners, employees – provides a very clear view of what is already known about the entity including their past interactions and relationships with other entities.

Flexible Rules-Based Alert Detection – A robust rules-based alert detection process must provide out-of-box functionality for the types of crimes outlined at the beginning of this article. At the same time, it should be flexible enough for an organization to modify or create rules as criminal activities evolve.

Predictive Analytics – Expected by analysts to become a 5.25B industry by 2018, predictive analytics ensures that big data is scrutinized and correlated with present and past historical trends. Predictive analytics utilizes a variety of statistics and modeling techniques and also uses machine information, data mining, and Business Intelligence (BI) tools to make predictions about the future behaviors including risk and fraud.

Social Network Analysis – Also known as Fraud Network Analysis, this emerging technology helps organizations detect and prevent fraud by going beyond rules and predictive analytics to analyze all related activities and relationships within a network. Knowing about shared telephone numbers, addresses or employment histories  allows companies to effectively ‘cluster’ groups of suspected financial crime perpetrators. The key here, however, is context. Many technologies can build these networks and clusters for review, but precious few can provide the key “what does this mean” element that business users require.

Investigation Management and Adjudication – Incorporating key elements of enterprise case management, collaboration, link visualization, information dissemination and knowledge discovery, this layer of functionality is designed to uncover insights which aid in investigating complex incidents. The result ought to be actionable visualization of critical entities, and documented results for potential litigation and regulatory compliance.

Anti-Money Laundering (AML) and Regulatory Compliance – With record fines being assessed to financial institutions globally, AML compliance is very clearly a major requirement within a financial crimes management solution. The oversight requirements grow almost daily, but at a minimum include out of box functionality for suspicious activity monitoring, regulatory reporting, watch list filtering, customer due diligence, Currency Transaction Report (CTR) processing, and the Foreign Account Tax Compliance Act (FATCA) compliance.

Now, there are clearly many more dynamics than can be summarized here but hopefully the point is made. The only way that organizations can continue to drive fraud and money laundering out is via a happy marriage between skilled financial crimes professionals and the flexible/adaptable technology that empowers them.

Posted by Douglas G. Wood. Click on ABOUT for more information.