The initiative aims to support firms in developing and testing transaction monitoring solutions by enabling access to realistic synthetic datasets and overcoming data sharing challenges.
Key insights include:
➡️ Use of realistic synthetic data: Generating realistic, privacy preserving dataset from real transactions, augmented with synthetic money laundering typologies;
➡️ Testing emerging technologies: The initiative enables firms to demonstrate the effectiveness of new and emerging technologies, including Artificial Intelligence (AI);
➡️ Defined problem statements: Firms can either demonstrate detection capabilities using unlabelled data or improve existing systems using labelled datasets; and
➡️ Assessing model effectiveness: The sprint explores performance, explainability, efficiency and accuracy of AML solutions.
✅ Firms should consider how synthetic data can support the development and testing of transaction monitoring models, enhance detection capabilities and address data access constraints.