Oculi：用于自动化信用风险分析的对话式智能体平台
Oculi: A Conversational Agentic Platform for Automated Credit Risk Analysis
浏览论文内容
中文总结 AI 辅助
研究人员推出对话式智能体平台Oculi，采用三层架构及结合确定性统计与LLM引导特征选择的细分发现流程，可自动完成信用风险分析，缩短洞察时间并保持严谨性，能发现手动探索难以处理的风险细分领域。
中文摘要 AI 辅助
金融机构的信用风险分析传统上需要分析师手动编写SQL查询、运行统计计算并构建可视化仪表盘，这一耗时的工作流程将探索范围限制在熟悉的细分领域。我们推出Oculi，这是一个将自然语言问题转化为全面信用风险分析的对话式平台，涵盖数据查询、统计测试和交互式可视化。Oculi采用三层架构，将推理（大语言模型驱动的智能体）、执行（模型上下文协议工具服务器）和展示（智能体用户界面）分离，使分析师能够发现高风险投资组合细分领域。在Oculi中，我们提出了一种新的细分领域发现流程，将确定性统计方法与大语言模型引导的特征选择相结合，利用大语言模型的语义领域知识和数据驱动指标来识别有意义、可操作的投资组合细分领域。在包含200多个特征的抵押贷款投资组合上进行评估，Oculi在发现手动探索此前难以处理的重要风险细分领域方面表现出有效性，显著缩短了洞察时间，同时保持了可审计性和统计严谨性。
英文摘要
Credit risk analysis in financial institutions traditionally requires analysts to manually write SQL queries, run statistical computations, and build visualization dashboards. This is a time-consuming workflow that limits exploration to familiar segments. We introduce \textbf{Oculi}, a conversational platform that transforms natural language questions into comprehensive credit risk analyses, complete with data queries, statistical testing, and interactive visualizations. Oculi employs a three-layer architecture that separates reasoning (LLM-powered agent), execution (Model Context Protocol tool servers), and presentation (agentic UI), enabling analysts to discover high-risk portfolio segments. Within Oculi, a new segment discovery pipeline is proposed that combines deterministic statistical methods with LLM-guided feature selection, leveraging LLM semantic domain knowledge alongside data-driven metrics to identify meaningful, actionable portfolio segments. Evaluated on a mortgage portfolio with 200+ features, Oculi demonstrates effectiveness in discovering material risk segments previously intractable through manual exploration, reducing time-to-insight significantly while maintaining auditability and statistical rigor.
发表机构
- Royal Bank of Canada（加拿大皇家银行）
- RBC Borealis
机构由 AI 辅助整理，请以论文原文为准。
