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.
Packaged financial crime solutions are built from the ground up by proven AI experts working alongside experienced AML professionals. Unlike other AI for AML approaches, packaged AI solutions are quick to implement and are continuously updated by the solution provider based on input from multiple customers and regulators.read more
Serving almost 20 million customers, the bank was concerned about the risks associated with false negatives that its current AML compliance technology was missing. Intent on driving financial crime out of its operation, the bank began searching for a solution that could enhance its existing rules-based transaction monitoring system (TMS) and minimize the risk related to undiscovered financial crime.read more
While all agree the promise of AI for AML is great, taking the steps to select and implement AI within an institution is relatively new. So, what is the best approach for implementing AI and machine learning into your efforts to combat financial crime?read more