We used a recursive modeling approach to study whether investors could, in real time, have used information on the comovement of stock markets to forecast stock returns in European stock markets for high-technology firms. We used weekly data on returns in the Neuer Markt, the Nouveau Marché,...

Using a random sample of 60% of our cross-sectional data on U.S. stocks from 1964 to 2012, we trained four machine learning algorithms to forecast debt paydown over a one-year horizon. An evaluation of these candidate models on half of the hold-out sample (20% of the original dataset) showed...