Anti-Money Laundering - Threat.Digital - Insights

Anti-Money Laundering

A collection of 2 posts

Threat.Digital model benchmarking process for selecting AI models for due diligence tasks

AI Models Keep Changing. Due Diligence Technology Has to Change With Them

The model that performs best for adverse media screening may not be the best one for entity disambiguation, watchlist adjudication, or risk extraction. We continuously benchmark models by task because model selection affects both the quality of the work and the cost of providing it.

Silhouetted robots with labels comparing transaction monitoring models, name matching algorithms, and large language models in AML.

Anti-Money Laundering

These Are Not the AML Models You Are Used to Validating

Large Language Models (LLMs) are not the kind of "models" AML programs have historically validated, and treating them as such causes practical failures.