Reported by Rachael Kennedy

In 2023 alone, global fraud incurred a staggering cost of $485 billion, as reported by the Nasdaq-Verafin Global Financial Crime Report.

This growing challenge is becoming increasingly acute for market participants, particularly with the advent of real-time payments, and can incur significant reputational damage in addition to financial cost. Fraudsters are constantly devising new tactics to exploit vulnerabilities in the cross-border payments ecosystem, leaving financial institutions struggling to keep pace.

Traditional fraud detection methods, relying on rules-based systems and manual monitoring, have proven inadequate in the face of this evolving threat landscape.

These approaches often fail to detect sophisticated, anomalous patterns of activity, resulting in missed opportunities to prevent fraudulent transactions before they occur. As the financial industry grapples with the escalating fraud crisis, the need for a more innovative, proactive, and collaborative approach has become increasingly apparent.Source: Nilson

Enter the AI-pilot

Swift, the global member-owned cooperative and the world’s leading provider of secure financial messaging services, has come up with a plan.

With its trusted position at the heart of the financial industry and the vast trove of transaction data flowing across its global network of over 11,500 institutions, Swift has realised that AI could be the perfect sidekick to help in the fight against financial crime.

At the end of May, it announced two  AI-based experiments in collaboration with its member banks. The first pilot aims to enhance Swift’s existing Payment Controls service, which helps financial institutions detect anomalies that could be indicative of fraud.

By leveraging an AI model trained on historical patterns of activity on the Swift network, the enhanced Payment Controls service will create a more nuanced and accurate picture of potential fraud activity. This innovative approach will enable financial institutions to identify and flag anomalous payments before they are executed, providing a critical layer of defence against cross-border payments fraud.

Importantly, this pilot will utilize the participating banks’ own live traffic data, ensuring the findings have real-world applicability and can be seamlessly integrated into their existing fraud prevention frameworks. Swift will work closely with the pilot participants to refine the AI-powered enhancement, with the ultimate goal of making it available to all 500+ Payment Controls customers worldwide.

Read full report: https://www.theglobaltreasurer.com/2024/06/06/could-ai-be-the-solution-to-cross-border-payment-fraud/?amp=1