As banks in the U.S. and Australia grapple with how to effectively launch faster payments, more will turn to big data and machine learning to help better manage expected upticks in fraud, says John O'Neill Jr., director of financial crime and analytics at DarkTower, formerly Queen Associates.
One key fraud-fighting step, O'Neill says in an interview with Information Security Media Group, is "taking information and then combining it into a single source of data that all the different business lines within a financial institution can look at."
But how can that information be translated into meaningful data that can be used to detect or even predict fraud before a real-time payment is transmitted? That's where machine learning comes in, O'Neill says.
"The important thing for businesses to remember, especially banks, is that when it comes to machine learning, it actually has to learn," he says. "So if I can equate that to a child: A child is given a bike and then they're able to ride it. But they first have to learn how to ride it. So in this big data realm, where we're trying to capture a lot of information and actually put it in so that it can be used to find trends, you have to teach it how to actually find fraud."
And not all fraud is perpetrated equally, he adds, which means more "teaching" and "learning" has to take place. "There are many different types of fraud that can be committed - everything from check fraud to online payment fraud to wire transactions. Any of these [big data/machine learning] implementations really need to understand what those things are that make up fraud and how fraud is committed in these specific environments."
In this interview (see audio link below photo), O'Neill also discusses:
- Why fraud teams must work closely with developers to ensure big data is properly gathered to make machine learning effective;
- The crucial role big data plays in the analysis of possible fraud links between different channels or touchpoints, such as IP addresses and phone numbers; and
- How behavioral biometrics can be used to complement big data and machine learning.
O'Neill has held key cybersecurity roles within financial crimes intelligence for more than 22 years. Before joining the cybersecurity firm DarkTower, he worked as the team leader for IBM's "red cell team," where he used analytics and big data to combat money laundering, fraud, synthetic identities and cyber-related issues. He also worked within Bank of America's global financial crimes and compliance division, where he was director of intelligence and analytics for the fraud investigations group.