Global financial institutions (FIs) process billions of transactions per year and create/store petabytes of data through Know Your Customer (KYC) and other related sources. According to Capgemini’s 2017 World Payments Report, more than 426 billion non-cash transactions alone were processed in 2016.
To manage the complexity and scale of the problem, FIs equip themselves with large compliance teams. Compliance teams are tasked with monitoring these transactions through Transaction Monitoring Systems (TMS) and well-designed Anti-Money Laundering (AML) programs. Failure to maintain effective compliance processes often results in hundreds of millions of dollars in fines, in addition to negative reputation for the institution. Despite these measures, one of the items often overlooked in compliance programs is the utilization of predictive analytics to assist with KYC, Enhanced Due Diligence (EDD), and Purpose of Account (POA) programs.
In contrast, the fields of artificial intelligence (AI) and machine learning offer unique capabilities to employ precise predictive analytics by analyzing various data sources available to FIs and their compliance teams.
Predictive analytics has the potential to assist FIs in detecting financial criminals, including drug traffickers, terrorists, and scammers, while preventing them from exploiting their firm. It’s these new technologies that are critical to FIs’ efforts in reducing the flow of illicit money through the global banking systems while ensuring compliance with a number of federal regulations.
Some of the most common data streams that FIs process daily are:
- Transactional data generated from core banking or accounting systems;
- Alerts/transactions generated from TMS;
- Internal e-mail systems;
- Scanned internal files related to trade finance and other lines of business;
- Travel and expense reporting systems, and;
- Third-party vendor files;
Predictive analytics, properly applied to these data streams, will strongly assist compliance teams and consequently enhance AML, insider threat, fraud, and FCPA detection and prevention programs. As a by-product of these improvements, AI and machine learning-powered predictive analysis will invariably enhance internal controls.
Within a plethora of AI techniques that are suitable for predictive analytics, the Holt-Winters forecasting algorithm is particularly noteworthy. When applied to information that may vary over time, this algorithm (and other variations of it) has the capability of efficiently analyzing historical data and establishing a comprehensive model of the underlying pattern. The computed model may then be used, for example, to predict future activity, detect abnormal behavior, and trigger pre-defined alerts to prevent completion of suspicious actions.
In a particular scenario, predictive analytics enhanced with AI can assist the compliance team in assessing normal/expected employee expenses, while predicting what a personal or business account will have in volume and value over an extended period of time. Machine learning can further track and learn subtle anomalies in the predictions, while temporarily blocking abnormal account activity and alerting compliance departments to investigate the case further.
Automating High-Risk Entity Reviews to Reduce Errors, Improve Efficiencies, and Ensure CDD Compliance
Federal bank regulatory agencies require that financial institutions regularly review and segment all their customers based on risk. While the Customer Due Diligence (CDD) Rule, which amended BSA regulations in 2018, does not stipulate how often reviews should be...
On January 1, 2021, the Anti-Money Laundering Act (“AMLA”) was enacted by Congress as part of the National Defense Authorization Act (NDAA). The AML Act has made emerging technologies, such as AI, machine learning, and quantum information sciences, a national...
Disruptive technologies are no longer the stuff of science fiction. They’re not even the “next big thing.” Successful firms are using them right now to automate manual processes in their AML programs.