Don’t Trust, Verify: Adaptive Multi-Agent Feature Engineering for Financial Fraud Detection
Feature engineering in tabular fraud detection is critical yet challenging to automate due to extreme class imbalance, which heavily penalizes spurious features. While Large Language Models (LLMs) can generate candidate features from dataset schemas, schema-level plausibility correlates poorly with actual predictive va
研究重點
Feature engineering in tabular fraud detection is critical yet challenging to automate due to extreme class imbalance, which heavily penalizes spurious features. While Large Language Models (LLMs) can generate candidate features from dataset schemas, schema-level plausibility correlates poorly with actual predictive va
為什麼值得關注
這個議題涉及 Crew Pocket、Crew Deck 的實作方向。可先評估現有做法,再決定是否安排小型實驗。
可以進一步驗證什麼?
- 閱讀原文,確認它解決的問題、實驗方法及適用限制
- 檢查相關功能現有做法,找出可比較的差異
- 用小型 PoC 驗證成功率、品質、延遲和實際成本
參考資料
Don’t Trust, Verify: Adaptive Multi-Agent Feature Engineering for Financial Fraud Detection ↗2026-11-14T00:00:00Z · 研究論文索引
延伸探索
相關研究
- Securing Autonomous Multi-Agent AI Systems: A Zero-Trust Framework for Threat Detection, Behavioral Monitoring, and Resilience in Enterprise Environments相同研究主題 · 2026-11-17
- From Code Completion to Agentic Development: A Survey of AI Coding Agents, Ecosystems, and Evolving Software Engineering Practice相同研究主題 · 2026-11-16
- Evaluating the use of LLM-based multi-agent systems for internal information sharing and access within manufacturing相同研究主題 · 2026-11-11