We develop early warning models for financial crisis prediction by applying machine learning techniques to macrofinancial data for 17 countries over 1870–2016. Most nonlin-ear machine learning models outperform logistic regression in out-of-sample predictions and forecasting. We identify...

We propose a granular framework that makes use of advanced statistical methods to approximate developments in economy-wide expected corporate earnings. In particular, we evaluate the dynamic network structure of stock returns in the United States as a proxy for the transmission of shocks through...

We nowcast world trade using machine learning, distinguishing between tree-based methods (random forest, gradient boosting) and their regression-based counterparts (macroeconomic random forest, linear gradient boosting). While much less used in the literature, the latter are found to outperform...

This paper exploits daily infrared images taken from satellites to track economic activity in advanced and emerging countries. We first develop a framework to read, clean, and exploit satellite images. Our algorithm uses the laws of physics (Planck's law) and machine learning to detect the heat...

The Great Recession has been characterised by the two stylized facts: the buildup of leverage in the household sector in the period preceding the recession and a protracted economic recovery that followed. We attempt to explain these two facts as an information friction, whereby agents are...

In 2001, government guarantees for savings banks in Germany were removed following a law suit. We use this natural experiment to examine the effect of government guarantees on bank risk taking, using a large data set of matched bank/borrower information. The results suggest that banks whose...

In 2001, government guarantees for savings banks in Germany were removed following a law suit. We use this natural experiment to examine the effect of government guarantees on bank risk taking, using a large data set of matched bank/borrower information. The results suggest that banks whose...

We study the relationship between banks' size and risk-taking in the context of supranational banking supervision. Consistently with theoretical work on banking unions and in contrast to analyses emphasising incentives under- pinned by the too-big-to-fail effect, we find an inverse relationship...

We evaluate the role of insider ownership in shaping banks' equity issuances in response to the global financial crisis. We construct a unique dataset on the ownership structure of U.S. banks and their equity issuances and discover that greater insider ownership leads to less equity issuances....

Following the financial crisis, the share of non-performing loans has significantly increased, while the regulatory guidelines on the Internal-Ratings Based (IRB) approach for capital adequacy calculation related to defaulted exposures remains too general. As a result, the high-risk nature of...