The many inefficiencies of legacy transaction monitoring systems (TMS) continue to hinder anti-money laundering (AML) programs. The United Nations Office on Drugs and Crime (UNODC) estimates that the amount of money laundered globally annually is two to five percent of global GDP, or $800 billion to $2 trillion in U.S. dollars. This is trillions of dollars linked to the money generated from crimes such as human trafficking, the drug trade, terrorism, white-collar crime, and other criminal schemes.
Despite the many inherent limitations of rule-based systems, the financial services industry continues to rely heavily on TMS for the identification of money laundering and other financial crimes. Transaction monitoring systems are essential in the maintenance of an AML program, however, there are two areas in which the legacy technology could be enhanced:
- The identification of transactions that represent serious risks for financial institutions. If a financial crime does not violate a stated rule, the TMS will not flag it and a high volume of risky transactions could potentially go undiscovered. It is estimated that 50 percent of financial crimes pass through TMS unnoticed.
- The reduction of false positive alerts that TMS create. With TMS, the search for anomalies will frequently catch the normal transactions of legitimate clients. These “false positive” alerts trigger time-consuming and expensive human investigations. The industry estimates that approximately 95 percent of the alerts generated by TMS are false positives.
By leveraging advancements in data science such as artificial intelligence (AI) and machine learning, financial institutions can set a new standard of AML compliance, mitigating regulatory risk more effectively and saving the industry billions of dollars in fines. The application of AI is a logical one that would not require financial institutions to replace their TMS, but instead allow them to keep systems in place while enhancing their AML ecosystems.
For instance, AI-based AML solutions can reduce false positives by cleansing and enriching data before transactions flow through an institution’s TMS. After transactions pass through the TMS, an AI solution can then analyze the transactional data to detect false negatives, or anomalous behaviors, that may have been missed.
Artificial intelligence-equipped solutions can analyze massive amounts of transactional and client information from a variety of sources such as TMS, Know Your Customer (KYC) databases, Lines of Business (LOB) customer information, as well as investigative databases, public Internet sources and the deep web.
With an AI system, AML data points can be pulled and consolidated automatically, the transactions scored for risk and the anomalies documented for AML investigators that can now evolve from researchers desperately fighting against the clock to unearth relevant data into analysts presented with automated financial crime reports that allow them to be better informed and make more accurate determinations.
For financial institutions, the time is now to deploy AI into their AML ecosystems. AI and machine learning hold the key to reducing risk related to financial crimes, addressing regulation, reducing operational cost through improved efficiency and, most importantly, effectively preventing criminals and terrorists from using the banking industry.
QuantaVerse published a paper that examines how financial institutions can apply AI and machine learning technologies into their AML ecosystems. Click here to read the full paper.