Share these talks and lectures with your colleagues
Invite colleaguesPractice paper
Harnessing synthetic data to address fraud in cross-border payments
Journal of Payments Strategy & Systems,
18
(3),
261-275
(2024)
Abstract
The sharing of data between financial institutions is widely recognised as a key component in the industry’s efforts to combat fraud. Broader access to multiple sources of financial data is also critical to the development of high-quality fraud detection mechanisms based on artificial intelligence (AI). Given the challenges relating to sharing real financial data across countries and institutions, the use of synthetic data has recently become critical to enabling the exploration of broader data sharing and supporting open collaboration in AI model development. To generate synthetic data that can substitute for real data, computer algorithms closely mimic the key statistical properties of genuine data, while strictly preserving the privacy and sovereignty of the source data. This paper presents the results of an ongoing exploration into the generation of high-utility synthetic datasets of cross-border payment transactions using transformer models and discusses its application to the development of AI-based fraud prevention solutions.
Keywords: cross-border; fraud; data sharing; artificial intelligence; synthetic data; privacy-safe
The full article is available to subscribers to the journal.
Author's Biography
Johan Bryssinck leads Swift’s artificial intelligence (AI) product and federated AI initiatives, driving AI adoption to enhance products and services and to innovate with customers. He oversees banking, vendor and FinTech partnerships to solve common industry challenges with AI. He has more than 20 years’ experience in leadership in corporate strategy, business transformation, innovation and technology. His work in the field of critical market infrastructures has included positions at Swift, CLS and Euroclear.
Tom Jacobs heads the Data Centre of Expertise at Swift and has worked in topics ranging from business intelligence consulting to sales and product development. Having previously designed analytical utilities to support central banks in macroprudential regulation and monetary policy, he is now researching the generation and evaluation of synthetic payments data. Tom holds master’s degrees in engineering and computer science from KU Leuven and a master’s degree in general management from Vlerick Business School.
Filippo Simini is a computer scientist in the Argonne National Laboratory’s Machine Learning and Artificial Intelligence Group. His work focuses on helping develop, run and evaluate high-performance computing applications that include machine learning and artificial intelligence components, often combined with traditional science and engineering simulations. Filippo’s interests include generative modelling, privacy-preserving artificial intelligence and anomaly detection.
Ravi Doddasomayajula is Lead Data Scientist in Swift’s AI Center of Excellence. His work focuses on developing machine-learning models to detect anomalous transactions in financial data, with an aspiration to build GPT-like models that can predict transactions, generate synthetic data and identify anomalies. He has been working in the field of data science for six years and holds a PhD in bioengineering from George Mason University.
Martin Koder is the AI Governance Lead at Swift, where he oversees the definition and implementation of standards for responsible artificial intelligence and AI governance. Prior to joining Swift, Martin was Senior Manager for Regulatory Strategy, Capital Markets at the London Stock Exchange Group; he has also held other policy and technology consulting positions. He holds a BSc from the London School of Economics and an MSc in artificial intelligence from City University London.
Francisco Curbera leads AI infrastructure innovation at Swift. He has previously held technical executive and senior management roles at IBM Watson Health and IBM Research, leading research and development in such emerging technologies as blockchain, health informatics, artificial intelligence and distributed computing. He received his PhD from Columbia University and is the author of over 50 publications and 17 patents.
Venkatram Vishwanath is a computer scientist at Argonne National Laboratory, and leads artificial intelligence and machine learning at the Argonne Leadership Computing Facility. His current focus is on architectures, algorithms, system software and workflows to facilitate data-centric applications on supercomputing systems. He has received best papers awards in such areas as high-performance parallel and distributed computing and large data analysis and visualisation, and is a recipient of the ACM Gordon Bell award
Chalapathy Neti is Head of Swift’s AI Center of Excellence. Prior to joining Swift, he held various executive roles at IBM, including VP, IBM Watson Education, responsible for developing a specialised AI platform on Hybrid Cloud for personalised learning; Director of Healthcare Transformation, responsible for launching and leading IBM’s initiative on Healthcare Transformation. He has a PhD from Johns Hopkins University specialising in neural networks. He has authored more than 75 publications and 30 patents.
