Generative AI Enhanced Financial Risk Management Information Retrieval
It addresses the problem of inefficient information retrieval for financial institutions and researchers, though it is incremental as it applies an existing method to new domain-specific data.
This paper tackles the challenge of extracting insights from financial regulatory documents by introducing RiskData, a dataset from 94 OSFI guidelines, and RiskEmbed, a finetuned embedding model that significantly improves retrieval accuracy in financial question-answering systems.
Risk management in finance involves recognizing, evaluating, and addressing financial risks to maintain stability and ensure regulatory compliance. Extracting relevant insights from extensive regulatory documents is a complex challenge requiring advanced retrieval and language models. This paper introduces RiskData, a dataset specifically curated for finetuning embedding models in risk management, and RiskEmbed, a finetuned embedding model designed to improve retrieval accuracy in financial question-answering systems. The dataset is derived from 94 regulatory guidelines published by the Office of the Superintendent of Financial Institutions (OSFI) from 1991 to 2024. We finetune a state-of-the-art sentence BERT embedding model to enhance domain-specific retrieval performance typically for Retrieval-Augmented Generation (RAG) systems. Experimental results demonstrate that RiskEmbed significantly outperforms general-purpose and financial embedding models, achieving substantial improvements in ranking metrics. By open-sourcing both the dataset and the model, we provide a valuable resource for financial institutions and researchers aiming to develop more accurate and efficient risk management AI solutions.