Regulatory Graphs and GenAI for Real-Time Transaction Monitoring and Compliance Explanation in Banking
This addresses the problem of automated, explainable compliance for banks, though it appears incremental as it combines existing graph and generative methods.
The paper tackles real-time transaction monitoring in banking by integrating graph-based modeling and generative AI, achieving 98.2% F1-score, 97.8% precision, and 97.0% recall in detecting suspicious behavior with natural language explanations.
This paper presents a real-time transaction monitoring framework that integrates graph-based modeling, narrative field embedding, and generative explanation to support automated financial compliance. The system constructs dynamic transaction graphs, extracts structural and contextual features, and classifies suspicious behavior using a graph neural network. A retrieval-augmented generation module generates natural language explanations aligned with regulatory clauses for each flagged transaction. Experiments conducted on a simulated stream of financial data show that the proposed method achieves superior results, with 98.2% F1-score, 97.8% precision, and 97.0% recall. Expert evaluation further confirms the quality and interpretability of generated justifications. The findings demonstrate the potential of combining graph intelligence and generative models to support explainable, audit-ready compliance in high-risk financial environments.