Project Aurora: the power of data, technology and collaboration to combat money laundering across institutions and borders

Updated 27 March 2024

The BIS Innovation Hub Nordic Centre is launching a new phase of Project Aurora, building on the findings of phase 1, which concluded in 2023. The new initiative aims to:

• build public-private stakeholder awareness, engagement and governance initiatives.
• deliver a series of research, analysis, discussion, experimental and learning initiatives.
• deliver an iterative series of real-world proofs-of-concept that could scale to a potential pilot.

According to the Financial Action Task Force (FATF), almost all large money laundering schemes span across borders and involve different business sectors. Meanwhile, financial institutions often face limitations in detecting potential suspicious networks and transactions due to their reliance on fragmented data and systems. 

The payments systems landscape involves a complex interplay of private and public entities, including commercial banks, payment services providers, fintech companies, central banks and regulatory authorities. This complexity and fragmentation created by the interconnected and complex financial systems across institutions and borders, is exploited by criminals to hide illicit funds. 

It is important to recognise that this ecosystem collectively generates an extensive volume of data, which holds a lot of potential for strengthening AML efforts. Acknowledging this opportunity, the FATF has identified several technologies such as privacy-enhancing technologies and advanced analytics that, when applied to payment data in collaborative analysis and learning (CAL) approaches, could be a game changer in improving AML efforts, while upholding data protection, privacy and information security.

The current AML approach employed by financial institutions to monitor transactions for suspicious activities is done in a siloed way, which is ineffective when a behavioural based approach with a holistic network view of payment data is required.

In 2023, BIS Innovation Hub (Nordic Centre) successfully concluded phase 1 of Project Aurora, a proof of concept that explored new ways of combating money laundering taking a data driven approach, by applying artificial intelligence, machine learning privacy enhancing technologies and network analysis. It did this using simulated CAL approaches across institutions at a national level and across borders, whilst protecting sensitive information.

Phase 1 of the project demonstrated that the application of these technologies in different CAL approaches are more effective in detecting money laundering networks than the current siloed and rules-based approach. It detected potentially up to 3 times more money laundering involved complex schemes and reduced false positives by up to 80%.

The findings from phase 1 identified that real world proof of concepts are essential to test the feasibility and practicality of different CAL approaches. Phase 1 also identified key legal, regulatory, data protection, technical and operational challenges that would need to be addressed as well as the need for experimental work on data standards. Finally, phase 1 identified that protecting against financial crime, while upholding user privacy is an important challenge – the BIS Innovation Hub London Centre will explore this via project Hertha.