One of the biggest trends in our industry these days is big data. Everything is in the data – it’s right there! Can you see it?
If you are like most community banks, the answer is no. The data you have is powerful. Most businesses would kill to have that kind of access to their client’s information, history, decisions, and behaviors. It’s not for lack of information that your financial institution (FI) may struggle with regulatory compliance issues surrounding AML and fraud compliance. It’s for lack of correlation of that information.
Advanced analytics can do just that – tying together disparate, seemingly unconnected strings and sources of data in a way that has previously been impossible in the community banking space. It does so in a way that will help your AML investigators understand what is actually happening with your clients. Getting a handle on this element of risk is also empowering for your investigators because they spend their time looking at real risks and not chasing down rabbit holes that are false alarms.
Another component of advanced analytics that is critical is the ability to “tune” your models appropriately. If the analytics are pointing in the direction of false positives, how can that be fixed? By refining the logic, either through manual tuning, or through machine learning. Machine learning is an entirely new concept for most community FIs, but it’s an exciting new technological advance that allows the machine to correct and amend modeling based on the data coming in. The success rate of that data ends up being investigated and ultimately is SAR reportable.
Machine learning isn’t new – your social media engines and search engines have been doing this for some time. It predictively understands what you’re most likely to be interested based on your previous activity and applies that logic on the fly. It’s a similar idea in the AML and fraud space – understanding and correlating patterns in behavior over time in a sophisticated way that we’ve never been able to achieve previously in the community banking space.
Check out this information from SAS.com on the evolution of machine learning:
Because of new computing technologies, machine learning today is not like machine learning of the past. It was born from pattern recognition and the theory that computers can learn without being programmed to perform specific tasks; researchers interested in artificial intelligence wanted to see if computers could learn from data. The iterative aspect of machine learning is important because as models are exposed to new data, they are able to independently adapt. They learn from previous computations to produce reliable, repeatable decisions and results. It’s a science that’s not new – but one that has gained fresh momentum.
While many machine learning algorithms have been around for a long time, the ability to automatically apply complex mathematical calculations to big data – over and over, faster and faster – is a recent development. Here are a few widely publicized examples of machine learning applications you may be familiar with:
- The heavily hyped, self-driving Google car? The essence of machine learning.
- Online recommendation offers such as those from Amazon and Netflix? Machine learning applications for everyday life.
- Knowing what customers are saying about you on Twitter? Machine learning combined with linguistic rule creation.
- Fraud detection? One of the more obvious, important uses in our world today.
This, my friends, is the future of AML, fraud detection, and prevention in our lifetimes.