GPT-4 Outperforms Human Analysts in Financial Statement Analysis

May 28, 2024

Researchers at the University of Chicago have found that large language models, specifically GPT-4, can analyze financial statements with greater accuracy than humans. The study suggests significant implications for the future of financial analysis and decision-making as AI becomes more commonplace. GPT-4 outperformed human analysts in analyzing financial reports without textual context, achieving an accuracy rate of 60% compared to the 53-57% range of human analysts. The model’s capabilities were attributed to its vast knowledge base and theoretical understanding, enabling it to draw conclusions from data patterns even without specific financial training.