Using novel data and machine learning techniques, we develop an early warning system for bank distress. The main input variables come from confidential regulatory returns, and our measure of distress is derived from supervisory assessments of bank riskiness from 2006 through to 2012. We...

There is evidence that machine learning (ML) can improve the screening of risky borrowers, but the empirical literature gives diverse answers as to the impact of ML on credit markets. We provide a model in which traditional banks compete with fintech (innovative) banks that screen borrowers...

Default correlation is a key driver of credit risk. In the Basel regulatory framework it is measured by the asset value correlation parameter. Though past studies suggest that the parameter is over-calibrated for mortgages — generally the largest asset class on banks' balance sheets — they...

We develop early warning models for financial crisis prediction using machine learning techniques on macrofinancial data for 17 countries over 1870–2016. Machine learning models mostly outperform logistic regression in out-of-sample predictions and forecasting. We identify economic drivers of...

We propose a generic workflow for the use of machine learning models to inform decision making and to communicate modelling results with stakeholders. It involves three steps: (1) a comparative model evaluation, (2) a feature importance analysis and (3) statistical inference based on Shapley...

Using quarterly data on FAS 157 fair value disclosures for US bank holding companies from 2008 to 2013, we test whether capital ratios and the effects of market discipline differ according to extent and nature of assets recognized under Level 3 standards. These standards offer management...

Using quarterly data on FAS 157 fair value disclosures for US bank holding companies from 2008 to 2013, we test whether capital ratios and the effects of market discipline differ according to extent and nature of assets recognized under Level 3 standards. These standards offer management...

We study the impact of higher capital requirements on banks' decisions to grant collateralized rather than uncollateralized loans. We exploit the 2011 EBA capital exercise, a quasi-natural experiment that required a number of banks to increase their regulatory capital but not others. This...

We study the impact of higher capital requirements on banks' decisions to grant collateralized rather than uncollateralized loans. We exploit the 2011 EBA capital exercise, a quasi-natural experiment that required a number of banks to increase their regulatory capital but not others. This...

This paper shows that US banks' increased geographic diversification is an important explanation for the decline of their liquidity buffers from 1976 to the 2008 crisis. Diversified banks also hold more illiquid small business loans, less liquid mortgages, and have higher net liquidity creation....