Featurespace bags funding from US, UK govs to build new financial crime detection solution
Financial crime and fraud prevention tech firm Featurespace has received funding from the UK and US governments to develop an AI-powered system to help banks and payments service providers (PSPs) detect financial crime.
The privacy enhancing technologies (PETs) Challenge Prize funding will be used to build a system that can spot cross-border money laundering, application fraud and APP fraud while protecting data privacy.
Launched in July 2022 by Innovate UK and the National Science Foundation in the US, the PETs Challenge Prize scheme is backed by the international payments organisation Swift.
The privacy-preserving solution developed by Featurespace will allow AI models to be trained on sensitive private data key to unearthing criminal activity without the need for organisations to reveal or share their raw data.
The solution will leverage federated deep learning and incorporate privacy-enhancing techniques such as k-anonymity and local differential privacy. Featurespace has until 24 January to build its AI prototype.
Featurespace director of innovation David Sutton says privacy-preserving collaborative AI “is a hard problem that no-one has yet solved” but the firm is confident it can meet the challenge.
“A successful outcome of this project is to make money laundering across borders and between banks much more difficult. If you make it harder to launder money, you make criminal activities less profitable.”