Over the years, technology’s ability to enhance economic processes has increased, and a notable achievement in this area is the use of artificial intelligence. Researchers at the University of Chicago tested the “GPT-4” model from OpenAI in analyzing financial data of companies listed on the stock exchange.
According to a study they conducted, it was found that GPT-4 significantly outperforms human financial analysts, even when provided with a few standardized and undisclosed financial statements and data. The results showed that the accuracy of the large linguistic model’s predictions approaches the performance of advanced machine learning models.
The researchers who published a research paper titled “Analysis of Financial Data Using Large Linguistic Models” concluded that GPT-4 is capable of analyzing financial data with an accuracy of up to 60% in predicting future profit growth.
Using the “train of thought” technique, researchers were able to empower GPT-4 to perform complex inferences and simulate human thought processes in financial analysis, reflecting the model’s strength and superior analytical capability.
Furthermore, researchers believe that large linguistic models could be powerful tools to simplify and improve the work of financial analysts, although it is not expected to replace them with artificial intelligence in the near future.
Finally, the researchers created an interactive web application for ChatGPT Plus subscribers showcasing GPT-4’s ability to conduct financial analysis, emphasizing the importance of independently verifying the accuracy of the results.
