New GPT-4 is better than humans at financial forecasting, a new study revealed.
According to Business Insider, a study conducted by the Booth School of Business at the University of Chicago found that GPT-4 did a better job of analyzing financial statements and making predictions.
The study used the ‘chain of thought’ prompts, which directed the AI model to calculate different financial ratios and identify the trends in financial statements.
As per the study, “Even without any narrative or industry-specific information, the LLM outperforms financial analysts in its ability to predict earnings changes. The LLM exhibits a relative advantage over human analysts in situations when the analysts tend to struggle."
The researchers noted, “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.”
Whereas the human analyst prediction accuracy was relatively low, about 50%.
The study said, “We find that the long-short strategy based on GPT forecasts outperforms the market and generates significant alphas and Sharpe ratios.”
The study author suggested that GPT-4’s ability to recognize business concepts and financial patterns without complete information indicates that technology should play a key role in financial decision-making.
