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...

This paper assesses the value of multiple requirements in bank regulation using a novel empirical rule‑based methodology. Exploiting a dataset of capital and liquidity ratios for a sample of global banks in 2005 and 2006, we apply simple threshold-based rules to assess how different...

Is human or artificial intelligence more conducive to a stable financial system? To answer this question, we compare human and artificial intelligence with respect to several facets of their decision-making behaviour. On that basis, we characterise possibilities and challenges in designing...

We study the implications of multi-period mortgage loans for monetary policy, considering several realistic modifications — fixed interest rate contracts, lower bound constraint on newly granted loans, and possibility for the collateral constraint to become slack — to an otherwise standard...

We develop a dynamic stochastic general equilibrium framework that can account for important macroeconomic and financial moments, given Epstein-Zin preferences, heterogeneous banking and third-order approximation methods that yield a time-varying term premium that feeds back to the real economy....

We build a semi-structural New Keynesian model with financial frictions to study the drivers of macroeconomic tail risk (‘GDP-at-Risk’). We analyse the empirically observed fat left tail of the GDP distribution by modelling three key non-linearities emphasised in the literature: 1) an...

Firms with high pre-crisis cash holdings invested significantly more than their cash-poor rivals during the global financial crisis and especially so during the recovery phase. This resulted in a persistent and growing investment gap between cash-rich and cash-poor firms. Cash especially...

Using unique data at transaction and counterparty identity level, we study the microstructure of the Swiss franc FX over‑the‑counter (OTC) derivatives market during a time of stress that was triggered by the decision of the Swiss National Bank (SNB) to remove the Swiss franc‑euro exchange...

We introduce machine learning in the context of central banking and policy analyses. Our aim is to give an overview broad enough to allow the reader to place machine learning within the wider range of statistical modelling and computational analyses, and provide an idea of its scope and...