Why AI is vital for transaction monitoring

With money laundering, terrorist financing and other financial crimes rising in an increasingly digitised world, the use of cutting-edge technology to deal with it is growing.

In a recent post by Sentinels, the company discussed why AI is important to conducting transaction monitoring and how it can help in the fight against financial crime.

The company said, “Many of the previously analogue formats of fighting financial crime are now in need of technological solutions to keep up with the digital world, transaction monitoring needs AI to handle the rapidly evolving landscape of payments and remittances.

“This is largely down to digitization itself, which has enabled the rapid growth of online banking and other transactional activities—investing, money transfers, currency exchange, purchases; it’s now easier than ever to access all of these things and more. Naturally, this is piling significant pressure on financial institutions that are expected to thoroughly monitor a rapidly growing number of non-cash transactions and quickly detect suspicious activity.”

With this considered, Sentinels remarked that it is the case that many banks and other FIs continue to use outdated, archaic tools and operate with immature ecosystems that rely on manual human input.

Many of these processes that use legacy technologies are unable to keep up and operate at the scale required in a digital economy – this is due to the fact transaction monitoring and AML in general is intense, data-heavy work, with the workload climbing each day.

Sentinels said, “The only viable solution for firms nowadays is to apply artificial intelligence (AI) and machine learning (ML) to their tech-led (not human-led) transaction monitoring. This will help them to build a robust decision support system by leveraging ML-powered predictive analytics which uses self-learning to continuously evolve with new data points and customer analysis.”

While it is possible for companies to deploy their own AI/ML ecosystems and apply transaction monitoring technology, many opt to use transaction monitoring solutions that are already powered by AI/ML so they can keep their focus on deploying fast automatic real-time transaction monitoring, Sentinels claims.

Why does transaction monitoring need AI? Sentinels said, “AI and ML have been game changers for many sectors, and finance is no exception. One reason transaction monitoring needs AI is that costs are rising as non-cash transaction volumes grow year on year, which has consequently led to large increases in the number of suspicious transactions that need to be looked at by compliance teams.

“Together, AI and ML provide an opportunity for firms to reduce the operational costs associated with transaction monitoring by automating the process on an unprecedented scale. Over time, AI-backed transaction monitoring systems can begin to understand transactions and build pattern recognition to quickly identify AML typologies, monitor high-risk jurisdictions, identify suspicious movement of funds, screen against sanctioned individuals, and highlight spikes in the value or volume of transactions. This makes the transaction monitoring process more accurate, efficient, and cost-effective as a result, well beyond what could be achieved by a human-led process. More importantly, however, it keeps you in line with your compliance obligations and reduces the risk of becoming the subject of punitive action by regulators.

“Given the current state of play with regard to the digital transformation, it can easily be argued that an AI-backed approach to transaction monitoring is the only viable solution due to the unrelenting increase in global non-cash transaction volume that it is enabling. This coupled with the inherent fallibility of humans makes for quite the compelling case for adopting an AI- and tech-led approach to transaction monitoring.”

Find the full post here.

Enjoyed the story? 

Subscribe to our weekly RegTech newsletter and get the latest industry news & research

Copyright © 2018 RegTech Analyst


The following investor(s) were tagged in this article.