<div>
 ChatGPT and Deepseek: Can They Predict the <span>Stock Market and Macroeconomy?</span>
</div>

We study whether ChatGPT and DeepSeek can extract information from the Wall Street Journal to predict the stock market and the macroeconomy. We find that ChatGPT has predictive power. DeepSeek underperforms ChatGPT, which is trained more extensively in English. Other large language models also underperform. Consistent with financial theories, the predictability is driven by investors’ underreaction to positive news, especially during periods of economic downturn and high information uncertainty. Negative news correlates with returns but lacks predictive value. At present, ChatGPT appears to be the only model capable of capturing economic news that links to the market risk premium.

Keywords: LLMs, ChatGPT, DeepSeek, Textual Analysis, Return Predictability

JEL Classification: C22, C53, G11, G12, G17

Suggested Citation: Suggested Citation

Chen, Jian and Tang, Guohao and Zhou, Guofu and Zhu, Wu,

ChatGPT and Deepseek: Can They Predict the Stock Market and Macroeconomy?

(July 31, 2023). Olin Business School Center for Finance & Accounting Research Paper No. 2023/18, Available at SSRN: https://ssrn.com/abstract=4660148 or http://dx.doi.org/10.2139/ssrn.4660148