Berlin Machine Learning - GANs for Anti Money Laundering

GANs for Anti Money Laundering; Running AI Models in the Cloud‍

Abstract: Deep learning delivers a lower number of false positives with higher accuracy than traditional rule-based approaches to anti money laundering (AML). However, supervised machine learning is not a viable approach due to the massive imbalance between the number of “good” and “bad” transactions. In this talk, we will go unsupervised and present our work on using GANs for anomaly detection for AML.