Machine Learning in the Global Fight Against Money Laundering and Terrorist Financing: An Affordance Perspective

Analytical summary by MSc. André Monteiro, originally published on Medium (August 2024) — condenses Canhoto, A. I., et al. (2021), “Leveraging machine learning in the global fight against money laundering and terrorism financing: an affordance’s perspective”, Journal of Business Research, 131, 441–452.

What you will find:

• The gap: the actual affordance of ML for AML detection at the studied bank was lower than the perceived one
• State of practice: AI/ML in AML is still more experimental than systematic, despite FATF promotion
• Technique fit: supervised for known patterns; unsupervised and boosting for real-time, evolving behaviour
• Practical limits: processing capacity, data quality, legacy-system silos, unstructured data
• Binding constraint: legal frameworks and data-sharing between banks and law enforcement

Format: PDF, 3 pages, English. Immediate download after purchase.