新闻
Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- Research combines gradient boosting, graph features, anomaly detection, and LLM agents for explainable fraud detection on transaction data.
- 为何重要
- Matters for engineers building fraud systems where auditability and human review are required alongside detection accuracy.
- 注意
- LLM investigation agent underperformed simple thresholding despite explanations and context, suggesting plausible rationales do not guarantee better decisions.
收听本摘要
- agent
- agentic
- llm
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。