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

TL;DR

This study evaluates ChatGPT and DeepSeek's ability to predict stock market and macroeconomic trends from Wall Street Journal data, revealing ChatGPT's superior predictive power linked to investor underreaction and economic news processing.

Contribution

The paper demonstrates that ChatGPT can effectively predict financial markets and macroeconomic indicators by extracting relevant information from news sources, outperforming other large language models.

Findings

ChatGPT shows significant predictive power for stock and macroeconomic trends.

DeepSeek underperforms compared to ChatGPT in financial prediction tasks.

Predictability is driven by investor underreaction to positive news during economic downturns.

Abstract

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.