ChatGPT may be able to predict stock movements, finance professors show

In a new working paper, Assistant Professor Alejandro Lopez-Lira and Emerson-Merrill Lynch Associate Professor Yuehua Tang find that large language models may be useful when forecasting stock prices.

They used ChatGPT to parse news headlines for whether they’re good or bad for a stock, and found that ChatGPT’s ability to predict the direction of the next day’s returns were much better than random. 

Read more in this story from CNBC.