Artificial Intelligence in BSA

Jill Cacic
January 8, 2020
Read Time: min

Artificial Intelligence in BSA/AML

Artificial intelligence is one of the biggest buzzwords in the anti-money laundering (AML) community. Some BSA professionals are excited for the promise of added security around transaction monitoring and fraud, while others are worried about the lack of security it provides their jobs.

The Financial Crimes Enforcement Network (FinCEN) understands the importance of utilizing technology in AML to better prevent bad actors from profiting off their illicit gains. In December 2018, FinCEN released the Joint Statement on Innovative Efforts to Combat Money Laundering and Terrorist Financing. It outlined the importance of financial institutions to use “innovative approaches” including artificial intelligence and other new technology to enhance their AML programs.

What is artificial intelligence?

Artificial intelligence, or AI, was defined in 1956 by John McCarthy as “the science and engineering of making intelligent machines,” or the development of computer systems that can perform tasks that require human intelligence. There are several different branches of AI, but here are the two most relevant to community financial institutions:

  • Robotic Process Automation (RPA) automates repetitive queries, calculations, and the maintenance of records and transactions. Where traditional workflow automation required coded actions to interface to back end systems through APIs (application programming interfaces), RPA systems learn by ‘watching’ the user perform the task in the application’s graphical user interface (GUI) and then repeat the tasks directly through the GUI.
  • Machine learning is the ability for systems to ‘learn’ without explicit programming. It encompasses several subtypes, but the two most discussed are supervised and unsupervised machine learning:
    • Supervised machine learning is accomplished by providing a large quantity of labeled data including the input and the desired output, and letting the machine determine the appropriate functions/algorithm needed to accomplish that goal.
      • For example, if someone fed a system thousands of pictures of appropriately labeled ducks, the system would learn how to correlate the images as ‘ducks.’ To test this, the system would receive additional unlabeled images of ducks and other items. The system would apply the function(s) and return data categorized as ‘ducks’ and ‘not ducks.’
    • Unsupervised machine learning consists of providing unlabeled data and no expected outcomes and letting the system find commonalities on its own. Presented with the same unlabeled ‘test’ data in the second example above, the system should be able to categorize the ‘ducks’ vs. ‘not ducks.’ It just would not be able to label the output.
    • Natural Language Processing (NLP) imitates a human‘s ability to write and read text in a language. An early example in this field is a chatbot named ELIZA that was created in 1964. It could simulate a text conversation by rephrasing the response from the original statement using hard-coded grammar rules.
    • Natural Language Generation (NLG), an offshoot of NLP, is a technology that turns data into plain-English language. In other words, it is software that can look at your data and write a story from it.
A BSA/AML software that's customized to your institution? That's big.
learn more

AI will never replace the human element in BSA

Artificial intelligence will never replace the human element that is necessary in dealing with the Bank Secrecy Act (BSA) and AML. A BSA officer’s best tool is his/her gut instinct and that can never be replicated by a machine. By utilizing AI to strengthen your BSA program, you are empowering yourself and your team to automate portions of your job, allowing you to spend more time finding potentially suspicious activity. Computers are better at uncovering patterns than humans are, so allow AI to automate some of the more tedious parts of your job. Because you are better at looking at an alert and knowing if it should be escalated to a case because your gut tells you something is off, that is where you should be spending your valuable and limited time.

Do you want to learn more about artificial intelligence and how it can help strengthen your BSA program? Sign up for our upcoming webinar AI, Machine Learning, and Your BSA/AML Program.

About the Author

Jill Cacic

Jill is a senior public relations specialist at Abrigo.

Full Bio

About Abrigo

Abrigo is a leading technology provider of compliance, credit risk, and lending solutions that community financial institutions use to manage risk and drive growth. Our software automates key processes — from anti-money laundering to fraud detection to lending solutions — empowering our customers by addressing their Enterprise Risk Management needs.

Make Big Things Happen.

 

Looking for Banker’s Toolbox? You are in the Right Place!

Banker’s Toolbox is now Abrigo, giving you a single source for all your enterprise risk management needs. Use the login button here, or the link in the top navigation, to log in to Banker’s Toolbox Community Online.

Make yourself at home!