Banking co-operative Swift is collaborating with global banks on AI pilots aimed at combating cross-border payments fraud.
In the initial pilot, Swift is enhancing its existing Payment Controls service, which helps financial institutions identify anomalies that may indicate fraud. The updated service will leverage an AI model to create a more nuanced and accurate assessment of potential fraud based on historical activity patterns within the global messaging network. These tests will utilize live traffic data from member banks to evaluate the model’s practical application.
In a separate initiative, Swift has gathered 10 prominent financial institutions to explore the use of advanced AI technology for analyzing anonymously shared data to detect potential fraud. This group includes BNY Mellon, Deutsche Bank, DNB, HSBC, Intesa Sanpaolo, and Standard Bank. They will experiment with secure data collaboration and federated learning technologies to extract insights and identify fraud patterns from a more comprehensive dataset.
Tom Zschach, chief innovation officer at Swift, remarked, "AI has great potential to significantly reduce fraud in the financial industry. That’s an incredibly exciting prospect, but it will require strong collaboration. Swift has a unique ability to unite financial organizations to harness the benefits of AI for the industry’s advancement, and we’re enthusiastic about the potential of both of these pilots to bolster the cross-border payments ecosystem."
For more insights into the challenges and opportunities artificial intelligence presents to the banking sector, join Finextra’s inaugural NextGenAI conference on November 26, 2024. Register your interest here.