ChatGPT can predict stock moves from headlines and decipher Fed statements - AI in Finance
The hype surrounding the use of artificial intelligence in the finance industry has been justified, according to two new research papers that have been published this month. The papers detail how AI chatbot, ChatGPT, was successfully used in deciphering Federal Reserve statements, as well as determining whether headlines are positive or negative for a stock. In both tests, ChatGPT was able to ace the tasks, showing the potential for technology to turn large amounts of text from social media, news articles, speeches, and more into trading signals.
While quants already use language models to inform many strategies, the findings point to OpenAI's NLP technology reaching a new level in terms of parsing nuance and context. In the first paper, titled “Can ChatGPT Decipher Fedspeak?”, researchers from the Federal Reserve found that ChatGPT came closest to humans in figuring out whether the central bank's statements were hawkish or dovish. The findings demonstrated that ChatGPT was able to explain its classifications of Fed policy statements in a way that resembled the central bank's own analyst. This impressive feat was achieved without the need for specific training.
The second study, “Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models”, found that ChatGPT showed a statistical link to the stock’s subsequent moves. In the study, ChatGPT was prompted to interpret corporate news headlines as a financial expert. Using news that was not covered in its training data, the chatbot was able to correctly parse the implications of the headlines and determine whether they were positive or negative for a stock.
The advances demonstrated by ChatGPT look set to open up whole worlds of new information and make the tech more accessible to a broader community of finance professionals. The possibilities of this technology are endless and could potentially speed up the whole process of interpreting data.
