This study provides a rigorous empirical comparison of structural and reduced-form credit risk frameworks. As major difference we focus on the discriminative modeling of default time. In contrast to previous literature, we calibrate both approaches to bond and equity prices. By using same input...

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...