Financial giant JPMorgan Chase introduces digital banking services in Germany.
Swift, a global financial messaging cooperative based in Belgium, has been exploring the role of Artificial Intelligence (AI) in financial services, with over 50 use cases ranging from proofs of concept to live applications. As part of this exploration, Swift has conducted experiments to demonstrate how AI and secure cross-border data collaboration can help reduce fraud in international payments.
The experiments, carried out in partnership with 13 global financial institutions, including ANZ, BNY, and Intesa Sanpaolo, applied privacy-enhancing technologies (PETs) to allow participants to exchange fraud-related insights securely across jurisdictions. This real-time verification of intelligence on suspicious accounts, enabled by PETs, has the potential to significantly shorten the time needed to identify international financial crime networks and prevent fraudulent payments.
One of the key findings from the experiments was that a model trained on synthetic data from ten million artificial transactions was twice as effective in detecting known frauds compared with one trained on a single institution's data. This underscores the power of a united, industry-wide fraud defense, a concept emphasised by Rachel Levi, Head of AI at Swift. According to Levi, a united defense will always be stronger than one put up by a single institution acting alone.
The experiments also demonstrated Swift's role as a trusted cooperative at the heart of global finance. Rachel Levi stated that these experiments are a testament to Swift's commitment to fostering collaboration and innovation to tackle the challenges faced by the industry.
In addition to the use of PETs, another case combined PETs with federated learning, an AI technique that trains models locally at each institution without sharing customer data. This approach allows for the benefits of collaboration without compromising on privacy and security.
Swift plans to expand participation before moving to a second phase of trials using real transaction data. The second phase of trials will assess the impact of the technologies in live environments, with the ultimate goal of significantly reducing the billions lost to fraud each year and allowing fraud to be stopped in minutes, not hours or days.
Earlier this year, Swift introduced an AI-enhanced Payments Controls Service. The cooperative's efforts to combat fraud in international payments are part of a broader commitment to ensuring the safety and security of the global financial system. As the world becomes increasingly interconnected, the need for effective fraud prevention measures has never been greater. Swift's experiments represent a significant step forward in this ongoing effort.
Despite extensive research, there are no search results explicitly naming other global financial institutions involved in Swift's attempts to reduce fraud controls in international payments. The cooperative has not released a list of all the institutions involved in the experiments.
Read also:
- Global Content Dissemination Through Cross-Linguistic Voiceovers
- Development of Restaurant Apps: Expenses and Essential Elements
- Time is of the essence
- European transportation's sustainability and competitiveness rely on a "green industrial agreement" that serves the interests of both corporations and residents, as discussed in an Editorial from August 2024.
