This NBER working paper examines the use of artificial intelligence (AI) in stock analysis. The authors build an AI analyst that can beat the majority of human analysts in stock price forecasts and generate excess returns. The AI model is able to digest corporate financial information, qualitative disclosure, and macroeconomic indicators. The authors find that the AI model outperforms human analysts in both accuracy and consistency. The study suggests that AI has the potential to significantly improve the efficiency of stock analysis.