I'm not sure I believe this result but interesting. I'd need some more rigor and peer review. And, if true, how much longer will it hold up if everyone else is using something similar to predict stock movement.
https://www.cnbc.com/2023/04/12/chat...ssor-says.html
Quote:
Alejandro Lopez-Lira, a finance professor at the University of Florida, says that large language models may be useful when forecasting stock prices.
He 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.
Lopez-Lira said he was surprised by the results, adding they suggest that sophisticated investors aren’t using ChatGPT-style machine learning in their trading strategies yet.
|