Corporate bonds carry a premium of extreme illiquidity (EIL). This premium permeates all rating categories and heightens in times of stress and periods with high uncertainty. EIL has predictive power in the cross-section for future returns up to at least a one-year horizon. Active investors like...

We propose a dynamic measure of stock market sentiment, extending heavily the widely adopted Baker and Wurgler (2006) market sentiment index construct on the novel basis that (1) the aggregate market sentiment must cover as many views from different investors or investment activities as possible;...

We propose a dynamic measure of stock market sentiment, extending heavily the widely adopted Baker and Wurgler (2006) market sentiment index construct on the novel basis that (1) the aggregate market sentiment must cover as many views from different investors or investment activities as possible;...

We use machine learning methods and high-dimensional detailed financial data to predict the direction of one-year-ahead earnings changes. Our models show significant out-of-sample predictive power: the area under the receiver operating characteristics curve ranges from 67.52% to 68.66%,...

We conduct a fundamental analysis of detailed financial information to predict earnings. Since 2012, all U.S. public companies must tag quantitative amounts in financial statements and footnotes of their 10-K reports using the eXtensible Business Reporting Language (XBRL). Leveraging machine...