Adaptive Temporal Graph Neural Networks for Real-Time Financial Fraud Detection under Concept Drift
Financial fraud detectors operate in a non-stationary environment in which illicit actors adapt, class prevalence changes, and labels arrive after investigation. This paper proposes ATGNN-SP, a drift-gated stable-plastic temporal graph neural network for real-time-compatible fraud scoring. Each directed transaction sna...
Xin-Ran Yue, Jing-Yun Yang, Ru-Feng Zhu et al.
· Highlights in Business, Econ... · 0 citations