PhD Student Graph Machine Learning & Financial Crime Analytics

This role involves developing machine learning methods to detect suspicious transaction patterns and complex anomalies in transaction and relationship networks for financial crime detection. The position focuses on researching modern approaches like Graph Neural Networks and self-supervised learning, particularly for scenarios with limited labeled data. The role also includes evaluating new methods for detection performance, robustness, and explainability, and translating suitable approaches into innovative AI solutions for banks and insurance companies.