Home » First Party Fraud (post 4 of 4) – A Use Case

First Party Fraud (post 4 of 4) – A Use Case

By Mike Betron, Infoglide VP of Marketing


Note: Today’s post is the fourth in our series on first-party fraud. The first article introduced First-Party Fraud (FPF) and explained why it is so dangerous for the banking industry. The second article provided a quantitative framework for assessing the amount of damage FPF typically causes, while our third article took a look at how criminals’ repeated use of false identity information leaves behind important clues which social link analysis uses to identify criminal networks and block potentially fraudulent activity. Our final article attempts to tie everything together by looking at a simple example of how social link analysis tools can detect bust-out fraud.

As discussed in our previous blog in this series, Social Link Analysis works by identifying linkages between individuals to create a social network. Social Link Analysis can then analyze the network to identify organized crime, such as bust-out fraud and internal collusion.

During the Social Link Analysis process, every individual is connected to a single network. An analysis at a large tier 1 bank will turn up millions of networks, but the majority of individuals only belong to very small networks (such as a husband and wife, and possibly a child).  However, the social linking process will certainly turn up a small percentage of larger networks of interconnected individuals. It is in these larger networks where participants of bust-out fraud are hiding.

Due to the massive number of networks within a system, the analysis is performed mathematically (e.g. without user interface) and scores and alerts are generated. However, any network can be “visualized” using the software to create a graphic display of information and connections. In this example, we’ll look at a visualization of a small network that the social link analysis tool has alerted as a possible fraud ring.




Figure 1: Visualization of a single social network discovered by Social Link Analysis

As you can see in Figure 1, this network starts off with Suzie Smith (upper left-hand corner), who has a checking account, a credit card, a charged-off loan (meaning a loan with debt that is unlikely to be collected) and an active loan at the bank.

However, an analysis of Suzie’s relationships begins to turn up some suspicious information.  Suzie Smith is connected to Jack Wilson (lower left-hand corner), another customer with the same phone number. Like Suzie, Jack has some charged-off credit, a credit card and a charged-off loan.

Additionally, Suzie Smith is linked to another individual, John Benton (upper right-hand corner), because they share the same address. Not only does John Benton have a charged-off loan, but one of his other loans is under investigation at the bank.

If fraud is not obvious at this point, it certainly is when the analysis looks at third-degree relationships. Jack Wilson is connected through an address match to Mark Rivera, who is under investigation for mortgage fraud, and Mark Rivera is connected to John Benton through a matching phone number. As a result, Social Link Analysis has detected four members of a network, each with various amounts of charged-off fraud.

By just looking at one individual’s data, people such as Suzie Smith and Jack Wilson might never get flagged because their connections are not immediately apparent. After all, with the exception of a charge-off here and there, they look like normal customers. In fact, in many cases of bust-out fraud, networks will look much “cleaner,” with fewer red flags. In these cases, analyzing connections, network size and formation are the only ways to discover bust-out fraud.


Advantages of SLA for Banks

As seen in the example above, SLA provides banks with an opportunity to identify crime networks before fraud takes place. In addition, SLA can help banks improve operational expenses and assist criminal investigators. Benefits of social network analysis include:

Infoglide’s Social Link Analysis quickly pieces together and distinguishes elements of a fraud network so that banks can address issues and implement solutions before being attacked, improving fraud detection and potentially saving thousands of dollars in bad debt and staff time. We’re proud to offer this new tool to the financial industry and are excited to see how it’s being used across the industry to stop crime.

Comments are closed.