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...

We use trade-level data to examine the role of actively managed funds (AMFs) in earnings news dissemination. We find AMFs are drawn to, and participate disproportionately more in, earnings announcements (EAs) that include bundled managerial guidance. When the two pieces of news are directionally...