Accurate probability-of-distress models are central to regulators, firms, and individuals who need to evaluate the default risk of a loan portfolio. A number of papers document that recent machine learning models outperform traditional corporate distress models in terms of accurately ranking...

This thesis consists of four chapters, all of which are related to credit risk and particularly modeling of default risk. The chapters can be read independently, and the intended audience differs somewhat among them. The first chapter is methodical; the intended audience consists of...

Corporate distress models typically only employ the numerical financial variables in the firms' annual reports. We develop a model that employs the unstructured textual data in the reports as well, namely the auditors' reports and managements' statements. Our model consists of a convolutional...

The sentiment of news predicts the short-term stock market performance of individual companies. We find that this association is solely due to the idiosyncratic informational content of an article. We transparently quantify the association between news sentiment and stock market performance of...

We construct novel proxies of physical and transition climate risks by conducting textual analysis of climate-change news over the period 2000-2018. This analysis uncovers four textual variables related to the topics of U.S. climate policy, international summits, natural disasters, and global...

We analyze micro-level data from the Danish credit register and find that female business owners pay higher interest rates on corporate loans than male owners. The gender gap is partly explained by differences in firm and loan characteristics. However, an economically and statistically...