We apply state-of-the-art financial machine learning to assess the return-predictive value of more than 45,000 earnings announcements on a majority of S&P1500 constituents. To represent the diverse information content of earnings announcements, we generate predictor variables based on various...

I use uniquely comprehensive data on financial news events to test four predictions from an asymmetric information model of a firm's stock price. Certain investors trade on information before it becomes public; then, public news levels the playing field for other investors, increasing their...