BIS Innovation Hub uses AI and data analytics for efficient money laundering detection


The BIS Innovation Hub has found that a number of key tech developments have proven to be superior for detecting money laundering networks.

According to BIS, employing payments data, privacy-enhancing technologies, artificial intelligence (AI) and increased cooperation for a behavioural-based analysis approach is superior for detecting money laundering networks compared to the prevailing rules-based methodology.

This conclusion comes amidst the burgeoning costs of financial crime compliance, which, according to a study by Lexis Nexis, grew by around $60bn, reaching $274bn between 2020 and 2022.

In a bid to pioneer novel solutions to the problem, the BIS Innovation Hub’s Nordic Centre, in conjunction with Lucinity, an Icelandic AI software-as-a-service enterprise, initiated Project Aurora. The proof of concept (PoC) utilised a broad synthetic dataset emulating domestic and international payments data. To safeguard sensitive information, privacy-enhancing technologies were used, allowing machine learning and other analytical tools to operate while data remains encrypted.

Project Aurora, while using the synthetic dataset, trained algorithms to discern various patterns associated with money laundering activities across institutions and countries. It explored different perspectives on the synthetic data to portray various monitoring scenarios, including siloed, national, and cross-border. Different methods of collaborative analysis, including centralised, decentralised, and hybrid models, were tested at both national and cross-border levels.

BIS commented on the outcome of the project stating that, “The results highlight the effectiveness of employing advanced analytics and technologies that adopt a behavioural-based analysis approach. This approach focuses on understanding the relationships between different individuals and businesses and identifying anomalies from normal behaviour. These methods proved more effective in detecting money laundering networks than the current rules-based approach, which is limited by its siloed nature.”

Copyright © 2023 RegTech Analyst

Enjoyed the story? 

Subscribe to our weekly RegTech newsletter and get the latest industry news & research

Copyright © 2018 RegTech Analyst


The following investor(s) were tagged in this article.