Neural networks cracked stock market logic through textual reports
Researchers from the University of Chicago found that advanced AI models can explain about 17% of stock price fluctuations on earnings report days, far surpassing traditional economic methods that explained at most 5%. The AI analyzed unstructured text from management forecasts and conference calls, revealing that investors react more to accompanying rhetoric than to the financial figures themselves.
OpenAI
Anthropic
Google/DeepMind

