Financial Statement Analysis with Large Language Models
This addresses the problem of automating financial analysis for investors and analysts, showing potential for LLMs to enhance decision-making, though it is incremental in applying existing models to a new domain.
The study tackled the problem of financial statement analysis by evaluating whether large language models (LLMs) like GPT-4 can predict firms' future earnings direction, finding that the LLM outperformed human analysts and matched a state-of-the-art ML model, with trading strategies based on its predictions achieving higher Sharpe ratios and alphas.
We investigate whether large language models (LLMs) can successfully perform financial statement analysis in a way similar to a professional human analyst. We provide standardized and anonymous financial statements to GPT4 and instruct the model to analyze them to determine the direction of firms' future earnings. Even without narrative or industry-specific information, the LLM outperforms financial analysts in its ability to predict earnings changes directionally. The LLM exhibits a relative advantage over human analysts in situations when the analysts tend to struggle. Furthermore, we find that the prediction accuracy of the LLM is on par with a narrowly trained state-of-the-art ML model. LLM prediction does not stem from its training memory. Instead, we find that the LLM generates useful narrative insights about a company's future performance. Lastly, our trading strategies based on GPT's predictions yield a higher Sharpe ratio and alphas than strategies based on other models. Our results suggest that LLMs may take a central role in analysis and decision-making.