DL-RL: Dual-Layer Graph Neural Networks with Curriculum Reinforcement Learning for Financial Fraud Detection
Financial fraud imposes estimated annual global losses exceeding $5.1 trillion, while digital payment fraud grows at over 30% per year.
PaySim
Product · 3 documents
Key number
99.82% %
PaySim Model Accuracy. International Journal of Informatics and Communication Technology (IJ-ICT) p.1
Key number
$9 trillion USD
Estimated Global E-Commerce Sales by 2027. International Journal of Informatics and Communication Technology (IJ-ICT) p.1
AI-Driven Predictive Analytics Framework for Financial Fraud Detection in Digital Transactions
On a six-million-transaction synthetic dataset, the proposed ensemble attains a recall of 0.9184 at a false-positive rate of 0.0186.
Deep Transformer Architectures for Real-Time E-Payment Fraud Detection Under Class Imbalance
Global losses from electronic payment fraud are estimated to reach around USD 48 billion globally by 2025.