Money laundering has evolved into distributed schemes that challenge traditional monitoring models.
According to the United Nations Office on Drugs and Crime (UNODC), the amount of money laundered worldwide each year is equivalent to 2% to 5% of global GDP: between USD 800 billion and USD 2 trillion1.
A new risk dynamic
The traditional model, built around large transactions, is now obsolete. The Financial Action Task Force (FATF) describes schemes characterized by2:
- Fragmented amounts.
- Use of mule accounts.
- Constant rotation of funds.
- High transaction frequency.
These are distributed structures, designed to go unnoticed.
The limits of traditional AML
Current systems have critical weaknesses:
- High false positive rates in alerts.
- Limited ability to detect complex relationships.
- A focus on isolated events rather than networks.
The result is operational overload and poor effectiveness at identifying real risk.
The RiskTech approach
RiskTech approaches AML from a structural perspective:
- Transaction network analysis.
- Identification of distributed patterns.
- Machine learning models.
The goal is not only to detect suspicious transactions, but to understand complex financial behavior.
Modern money laundering doesn't try to hide: it tries to look normal. And normal isn't detected with rules; it's understood with intelligence.
Sources
- UNODC: Money laundering – Overview. View source
- FATF: Professional Money Laundering (2018). View source
