OpenAI's ChatGPT-4 Has A 'Relative Advantage' Over Humans In Financial Analysis, Study Finds: 'Even Without Any Narrative Or Industry-Specific Information'

A study conducted by the Booth School of Business at the University of Chicago found OpenAI’s GPT-4 more proficient than humans in financial analysis and forecasting, even without industry-specific information.

What Happened: The study which was made public last week, revealed that GPT-4, a large language model, excelled in analyzing financial statements and predicting future earnings, reported Business Insider.

“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.”

See Also: Elon Musk, Meta AI Chief Yann LeCun Have A Public Spat — Again: ‘Like His Cars, His Rockets…Dislike His Vengeful Politics’

As per the study, the model was able to identify trends in financial statements and calculate various financial ratios using “chain-of-thought” prompts. This led to more accurate predictions of future earnings compared to human analysts.

“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 prediction accuracy of the human analysts was closer to the low 50% range.

The study also found that trading strategies based on GPT-4’s forecasts were more profitable than the stock market, with higher share ratios and alpha. “We find that the long-short strategy based on GPT forecasts outperforms the market and generates significant alphas and Sharpe ratios.”

Subscribe to the Benzinga Tech Trends newsletter to get all the latest tech developments delivered to your inbox.

Why It Matters: The study’s findings could have significant implications for the financial services industry, which is increasingly adopting generative AI technologies. This development comes on the heels of OpenAI’s unveiling of GPT-4o, the latest version of its ChatGPT bot that can reason across audio, vision, and text.

Meanwhile, GPT-4 was launched in March 2023. At its launch, OpenAI described GPT-4 as a large multimodal model (accepting both image and text inputs and generating text outputs) that, despite being less capable than humans in many real-world scenarios, demonstrates human-level performance on various professional and academic benchmarks.

OpenAI’s ChatGPT model was introduced to the public in November 2022. By January of the following year, ChatGPT had registered 100 million users, achieving this milestone just 64 days after its launch.

Photo Courtesy: Shutterstock.com

Check out more of Benzinga’s Consumer Tech coverage by following this link.

Read Next: Economist Paul Krugman Says Degradation Of Google And Other Search Engines Are Making His Job Difficult: ‘And AI Is Worse Than Useless’

Disclaimer: This content was partially produced with the help of Benzinga Neuro and was reviewed and published by Benzinga editors.