A new research paper reported that GPT-4 can outperform human analysts when it comes to predicting the future on the basis of financial statement analysis.
The research paper was published in a preprint journal. The research paper seems to have extracted from its tests that GPT-4 gave better results compared to human counterparts in the short-term period (ranging between one month to six months).
The results are expected to have achieved about 60.31 percent accuracy in its predictions compared to 56.7 percent of human analysts. However, the paper seems to have not suggested that the AI model could replace humans.
What are the findings?
The“Financial Statement Analysis with Large Language Models” was published in the preprint journal Social Science Research Network (SSRN). It looks like that the 54-page paper attempted to find out the role conventional AI models can play in analysing the financial statements of an organisation. The paper also shows how AI can help in predicting the performance in the stock market in the near future.
“The CoT method asked GPT-4 to identify notable trends, compute key financial ratios, and to form expectations about future earnings. While the simple prompt did not fetch noteworthy results, the CoT prompts achieved 60.31 percent which was higher than the average human analyst’s performance,” The paper highlighted.
GPT-4 research paper: A detailed look
“We find that an LLM excels in a quantitative task that requires intuition and human-like reasoning. The ability to perform tasks across domains points towards the emergence of Artificial General Intelligence,” the paper explained.
However, the researchers highlighted that GPT and human analysts can be complementary instead of the former replacing the latter. Additionally, the paper claimed that LLMs have an advantage in areas where humans tend to show bias and disagreement.
Moreover, unlike GPT, humans can add value when analysis requires additional contextual information which might not be available within the financial data.
Follow FE Tech Bytes on Twitter, Instagram, LinkedIn, Facebook
