Back to Blog

Featurespace Secures Funding to Develop AI-Powered AML Prototype

Featurespace Secures Funding to Develop AI-Powered AML Prototype
  • U.K.-based fraud and financial crime prevention company Featurespace secured funding to help build an AI-powered prototype to fight money laundering and other financial crimes.
  • The funding comes from both the U.S. and U.K. governments, and is part of an initiative supported by Innovate UK, the U.S. National Science Foundation, and messaging network SWIFT.
  • Featurespace made its Finovate debut at FinovateEurope in 2016.

Fraud and financial crime prevention specialist Featurespace has secured funding from both the U.S. and U.K. governments to build an AI-powered technology to help financial services institutions – including banks and payment service providers (PSPs) – to detect and stop financial crime. The goal specifically is to enhance the ability of financial institutions to combat cross-border money laundering, application fraud, and APP fraud, in particular. The U.K.-based company, headquartered in Cambridge, will build a prototype, leveraging AI, that will be trained on “sensitive private payments data.” Featurespace will apply federated deep learning to the data, using privacy-enhancing techniques such as k-anonymity and local differential privacy. Organizations will not have to reveal, share, or combine their raw data in the process.

“U.K. and U.S. governments want banks to work together to stop fraud and money laundering,” Featurespace Director of Innovation David Sutton said. “This type of privacy-preserving collaboration AI is a hard problem that no one has yet solved. We are confident we can meet this challenge. We’re the only company in this project that has deployed innovative tech to fight worldwide financial crime – and we have the banking customers to prove it.”

The funding comes courtesy of the privacy enhancing technologies (PETs) Challenge Prize, an effort begun in July by Innovate UK and the U.S. National Science Foundation. The initiative also is supported by bank-owned messaging network SWIFT. Featurespace has been given a deadline of January 24 to build the prototype. Upon completion, if the project is successful, it will be showcased at the second Summit for Democracy to be convened in the U.S. in the first half of 2023.

“A successful outcome of this project is to make money laundering across borders and between banks much more difficult,” Sutton said. “If you make it harder to launder money, you make criminal activities less profitable. This will benefit businesses, society, and consumers.”

Founded in 2008, Featurespace made its Finovate debut at FinovateEurope in 2016. More than 70 direct customers and more than 200,000 institutions ranging from HSBC and Worldpay to fellow Finovate alums like TSYS and Marqeta, rely on Featurespace’s technology to protect themselves against fraud and financial crime. An innovator in the field of fraud prevention, Featurespace has developed technologies like Adaptive Behavioral Analytics and Automated Deep Behavioral Networks to profile both authentic and fraudulent behavior to combat financial crime in real-time. Both technologies are components of Featurespace’s ARIC Risk Hub.

Last week, Featurespace announced a partnership with Railsr to help customers of the embedded finance platform better defend themselves from fraud and financial crime. Per the agreement, Railsr’s fraud teams will be able to leverage card and payment fraud prevention and AML solutions via Featurespace’s ARIC Risk Hub.

“As embedded finance increasingly becomes expected by consumers, making sure they are protected from fraud and financial crime must be expected in equal measure,” Featurespace Chief Commercial Officer Matt Mills said. “Railsr (has) recognized this early and added a critical layer of self-learning technology to ensure their customers get only the best experience.”


Photo by Markus Spiske