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 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...

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...

This paper provides the first empirical evidence that bank regulation is associated with cross-border spillover effects through the lending activities of large multinational banks. We analyze business lending by 155 banks to 9613 firms in 1976 different localities across 16 countries. We find...

Using a novel panel data set we study the macroeconomic determinants of nonperforming loans (NPLs) across 75 countries during the past decade. According to our dynamic panel estimates, the following variables are found to significantly affect NPL ratios: real GDP growth, share prices, the...

This paper empirically examines the role of soft information in the competitive interaction between relationship and transaction banks. Soft information can be interpreted as a private signal about the quality of a firm that is observable to a relationship bank, but not to a transaction bank. We...

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...

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....

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 analyse the impact of the adoption of expected credit loss accounting (IFRS 9) on the timeliness and potential procyclicality of banks' loan loss provisioning. We use granular loan-level data from the euro area's credit register and investigate both firm-level credit events and macroeconomic...