Oculi: A Conversational Agentic Platform for Automated Credit Risk Analysis
Artificial IntelligenceMachine Learning
Summary
The authors created Oculi, a tool that lets financial analysts ask questions in plain language and get detailed credit risk reports automatically. Instead of writing complex code and doing manual data analysis, the system uses AI to handle data queries, statistics, and visualizations. Their approach combines traditional statistical methods with AI-guided feature selection to find important risk groups in mortgage data. Tests show Oculi finds meaningful risk segments faster and more thoroughly than manual methods, while keeping results clear and trustworthy.
credit risk analysisSQL queriesstatistical testinglarge language models (LLM)feature selectionportfolio segmentationinteractive visualizationmodel context protocolmortgage portfolio
Authors
Vennise Ho, Kristian Diana, Sandy Mourad, Milena Pilipovic, Vineel Nagisetty, Hossein Hajimirsadeghi
Abstract
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.