Agentic AI Systems Applied to tasks in Financial Services: Modeling and model risk management crews
Izunna Okpala, Ashkan Golgoon, Arjun Ravi Kannan
TL;DR
This paper investigates applying agentic AI systems to financial services, focusing on modeling workflows and model risk management. It proposes two coordinated crews with human-in-the-loop oversight to perform end-to-end financial modeling and risk assessment. The architecture leverages memory streams, role-playing agents, and guardrails within a CrewAI framework to enable modular, auditable workflows. Experiments on credit fraud detection, credit approval, and portfolio risk demonstrate strong performance and robust governance, highlighting practical implications for safe, scalable finance AI deployments.
Abstract
The advent of large language models has ushered in a new era of agentic systems, where artificial intelligence programs exhibit remarkable autonomous decision-making capabilities across diverse domains. This paper explores agentic system workflows in the financial services industry. In particular, we build agentic crews with human-in-the-loop module that can effectively collaborate to perform complex modeling and model risk management (MRM) tasks. The modeling crew consists of a judge agent and multiple agents who perform specific tasks such as exploratory data analysis, feature engineering, model selection/hyperparameter tuning, model training, model evaluation, and writing documentation. The MRM crew consists of a judge agent along with specialized agents who perform tasks such as checking compliance of modeling documentation, model replication, conceptual soundness, analysis of outcomes, and writing documentation. We demonstrate the effectiveness and robustness of modeling and MRM crews by presenting a series of numerical examples applied to credit card fraud detection, credit card approval, and portfolio credit risk modeling datasets.