Unfortunately, Sams story (Part 1, Part 2) is not an isolated case, nor was his reason for doing it particularly sophisticated. Motivation behind insider fraud can go from wanting to buy a bigger engagement ring to market profitability, like manipulating the Libor rates. Last year, internal banking fraud cost an estimated $47 billion and most of this went undetected. But Sam wasn't so lucky, his crime was identified through an advanced system that tracked and alerted the bank to unusual behaviour.
Standard banking software alone, no matter how smart, cannot solve the issue of insider fraud because people, systems and patterns constantly change. Where there are fingers and keyboards, there is the opportunity to commit fraud. To adapt to this changing environment you need an intelligent solution and rigorous processes. Standard transaction analytics can not usually see the actions that lead up to internal fraud. However, if a solution is able to correlate human behavior actions and information, regardless of how small and subtle, from across a banks systems then insider fraud can be addressed.
For insider fraud to be quickly and accurately detected it the solution must be multi-channel and multi-layer. It must be flexible enough to easily fit into any banking architecture, with preset connectors for any core banking platform, database, operating system or network device. To see the 'big picture' it needs to be able to analyze events and identify atypical behavior on a large scale using Big Data technology and predictive analytics to combine and standardize data. This approach means that a complete, real-time view is available from all perspectives, enabling you to immediately detect any suspicious activity and be alerted right away even before fraud happens when fraud has occurred.
A specialist, intelligent solution gives you the power to stop fraud before it's too late; ensuring 2016's banking frauds costs don't include some of your bottom line.