Using machine learning and many predictors, we find strong bond return predictability, with an out-of-sample R-squared of 4.48% and an annualized Sharpe ratio of 3.27. ML models identify important predictors for aggregate predictors (bond market returns, TERM and HML factors, GDP growth) and bond characteristics (downside risk, short-term reversal, return skewness, and credit spreads). Predictability varies over time, being stronger during periods of high investor risk aversion, slow economic growth, and strong cross-sectional factor explanatory power. Our results highlight the benefits of leveraging both cross-sectional and time-series predictors to forecast corporate bond returns while considering public and private bonds.

The widely-used Baker and Wurgler (2006) sentiment index is strongly correlated with business cycle variables, especially the short interest rate and Lee (2011) liquidity risk factor. The power of the sentiment index to predict cross-sectional stock returns is mainly driven by its information content related to these business cycle variables. About 63% percent of the total variation in the investor sentiment index can be explained by well-known, contemporaneous risk/business cycle variables. We decompose the widely used investor sentiment index into two components: one related to standard risk/business cycle variables and the other unrelated to those variables. We show that the power of the sentiment index to predict cross-sectional stock returns is mainly driven by the risk/business cycle component, while the residual component has little significance in predicting cross-sectional stock returns.

Using multiple short-sale measures, we examine the predictive power of short sales for future stock returns in 38 countries from July 2006 to December 2014. We find that the days-to-cover ratio and the utilization ratio measures have the most robust predictive power for future stock returns in the global capital market. Our results display significant cross-country and cross-firm differences in the predictive power of alternative short-sale measures. The predictive power of shorts is stronger in countries with nonprohibitive short sale regulations and for stocks with relatively low liquidity, high shorting fees, and low price efficiency.

This paper investigates the relation between media coverage and offering yield spreads using a comprehensive dataset of 5,338 industrial bonds issued from 1990 to 2011. We find that media coverage is negatively associated with firms’ cost of debt. This association is robust to controlling for standard yield determinants, different model specifications, and endogeneity. We identify 4 economic channels through which media coverage influences the cost of debt: Information asymmetry, governance, liquidity, and default risk. Importantly, media coverage has an independent influence beyond the effects of these economic mechanisms and is not a proxy for other firm attributes.