We compared the predictive performance of a series of machine learning and traditional methods for monthly CDS spreads, using firms' accounting-based, market-based and macroeconomics variables for a time period of 2006 to 2016. We find that ensemble machine learning methods (Bagging, Gradient...

We propose an original method to estimate the market price of risk under stress, which is needed to correct for risk aversion the CDS-implied probabilities of distress. The method is based, for simplicity, on a one-factor asset pricing model. The market price of risk under stress (the...

This paper finds that systematic default risk, or the event of widespread defaults in the corporate sector, is an important determinant of equity returns. Moreover, the market price of systematic default risk is one order of magnitude higher than the market price of other risk factors. In...