This report summarises the work we have done, jointly with the Turing Institute and Plenitude Consulting, to generate a synthetic data set that will be used to foster innovation in the detection of money laundering.
Read the research note (PDF)[2]
Progress in combatting money laundering depends on access to detailed financial data, yet legal and privacy constraints often restrict sharing of such information.
This project aims to tackle these challenges by collaborating with the Alan Turing Institute[3], Plenitude[4], and Napier AI[5] to create a fully synthetic dataset created using real data from UK retail banking, enhanced with realistic synthetic money laundering scenarios observed in financial markets.
We hope this project will show that synthetic data can help regulators and firms work together, supporting beneficial innovation in the detection of money laundering.
Next steps
The FCA will make this dataset available through the Digital Sandbox[6] as part of the upcoming Synthetic Data AML Solution Sprint, inviting firms to take part to demonstrate how new technologies such as AI can help in the fight against money laundering. Participants will use the data throughout the sprint and reconvene to share insights on how synthetic data can support innovation in the fight against financial crime.
Further details for firms that wish to apply for the Data Sprint can be found here[7] – applications close on 26 April 2026.
Authors
Leo Gosland, Henrike Mueller, Olivia Kearney, Stratis Limnios, Paul Mclear.
Disclaimer
Research notes contribute to the work of the FCA by providing rigorous research results and stimulating debate. While they may not necessarily represent the position of the FCA, they are one source of evidence that the FCA may use while discharging its functions and to inform its views. The FCA endeavours to ensure that research outputs are correct, through checks including independent referee reports, but the nature of such research and choice of research methods is a matter for the authors using their expert judgement. To the extent that research notes contain any errors or omissions, they should be attributed to the individual authors, rather than to the FCA.