Study Shows ChatGPT Can Predict Stock Market Movements

A new study conducted by finance professors from the University of Florida shows the potential value of ChatGPT in predicting stock market movements, Jeannine Mancini reported for Benzinga.com.

Photo Insert: ChatGPT outperformed traditional sentiment analysis methods that also used data from headlines and social media to predict stock movements.

In the study, more than 50,000 news headlines about companies dating back to October 2021 were fed to the chatbot, which evaluated whether the news was good, bad or irrelevant to the company's stock prices.

Using sentiment analysis, the chatbot generated a "ChatGPT score," which was then analyzed to determine whether it was predictive of the companies' stock market performance the following day.

The study found a significant positive correlation between the ChatGPT scores and the next-day stock performance for the analyzed companies. Companies with higher scores tended to have better returns than those with lower scores.

ChatGPT outperformed traditional sentiment analysis methods that also used data from headlines and social media to predict stock movements.

The researchers concluded that incorporating advanced language models such as ChatGPT into investment decision-making processes can lead to more accurate predictions and enhance the performance of quantitative trading strategies.

The study demonstrated that traditional models did not provide any additional predictive power over ChatGPT-derived sentiment scores. These findings suggest that ChatGPT may hold promise for investors seeking to anticipate future stock market movements.

WEEKLY FEATURE : MVP Group Keeps Lights On During Pandemic