This article originally appeared on Business Insider.
OpenAI’s GPT-4 proved to be a better financial analyst than humans, according to a new study.
The findings could upend the financial services industry that, like other business sectors, is racing to adopt generative AI technologies.
According to the study conducted by the Booth School of Business at the University of Chicago, the large language model did a better job of analyzing financial statements and making predictions based on those statements.
“Even without any narrative or industry-specific information, the LLM outperforms financial analysts in its ability to predict earnings changes,” the study said. “The LLM exhibits a relative advantage over human analysts in situations when the analysts tend to struggle.”
The study utilized “chain-of-thought” prompts that directed GPT-4 to identify trends in financial statements and calculate different financial ratios. From there, the large language model analyzed the information and predicted future earnings results.
“When we use the chain of thought prompt to emulate human reasoning, we find that GPT achieves an accuracy of 60%, which is remarkably higher than that achieved by the analysts,” the study said. The human analysts were closer to the low 50% range with regard to prediction accuracy.
The large language models’ ability to recognize financial patterns and business concepts with incomplete information suggests that the technology should play a key role in financial decision-making going forward, according to the study’s authors.
Finally, the study found that applying GPT-4’s financial acumen to trading strategies produced more profitable trading, with higher share ratios and alpha that ultimately beat the stock market.
“We find that the long-short strategy based on GPT forecasts outperforms the market and generates significant alphas and Sharpe ratios,” the study said.
Read the full article here
