Swift Is Testing AI to Fight Fraud

Swift, the banking cooperative, is collaborating with global banks to pilot artificial intelligence (AI) technologies aimed at combating cross-border payment fraud, according to Finextra.

In the initial pilot, Swift is enhancing its Payment Controls service, which currently helps financial institutions detect potential fraud by identifying anomalies. The enhancement involves integrating an AI model to create a more detailed and accurate picture of potential fraud based on historical patterns within the global messaging network. This model will be tested using live traffic data from member banks to assess its real-world applicability.

Additionally, Swift has brought together 10 leading financial institutions, including BNY Mellon, Deutsche Bank, DNB, HSBC, Intesa Sanpaolo, and Standard Bank, to experiment with advanced AI technology. This initiative will focus on using secure data collaboration and federated learning technologies to analyze anonymized data and detect potential fraud. The goal is to leverage a more extensive dataset to gain insights and identify fraud patterns.

«AI has great potential to significantly reduce fraud in the financial industry. That’s an incredibly exciting prospect, but one that will require strong collaboration. Swift has a unique ability to bring financial organisations together to harness the benefits of AI in the interests of the industry, and we’re excited by the potential of both of these pilots to help further strengthen the cross-border payments ecosystem,» said Tom Zschach, chief innovation officer at Swift.