Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation

За 30 секунд

Что произошло

Research combines gradient boosting, graph features, anomaly detection, and LLM agents for explainable fraud detection on transaction data.

Почему это важно

Matters for engineers building fraud systems where auditability and human review are required alongside detection accuracy.

На что обратить внимание

LLM investigation agent underperformed simple thresholding despite explanations and context, suggesting plausible rationales do not guarantee better decisions.