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...

This paper investigates the power of macroeconomic factors to explain euro area bond risk premia using (i) a large dataset that captures the nowadays data-rich environment (ii) the Elastic Net variable selection. We find that macroeconomic factors, in particular economic activity and sentiment...

In this paper we propose a composite indicator that measures multi-dimensional sovereign bond market stress in the euro area as a whole and in individual euro area member states. It integrates measures of credit risk, volatility and liquidity at short-term and long-term bond maturities into a...

Early-warning models most commonly optimize signaling thresholds on crisis probabilities. The expost threshold optimization is based upon a loss function accounting for preferences between forecast errors, but comes with two crucial drawbacks: unstable thresholds in recursive estimations and an...

The paper uses the Self-Organizing Map for mapping the state of financial stability and visualizing the sources of systemic risks as well as for predicting systemic financial crises. The Self-Organizing Financial Stability Map (SOFSM) enables a two-dimensional representation of a...

This paper develops a framework for assessing systemic risks and for predicting (out-of-sample) systemic events, i.e. periods of extreme financial instability with potential real costs. We test the ability of a wide range of “stand alone” and composite indicators in predicting systemic...

The paper develops an early-warning model for predicting vulnerabilities leading to distress in European banks using both bank and country-level data. As outright bank failures have been rare in Europe, the paper introduces a novel dataset that complements bankruptcies and defaults with state...

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...

We assess the ability of yield curve factors to predict risk premia in short-term interest rates and exchange rates across a large sample of major advanced economies. We find that the same tick-shaped linear combination of (relative) bond yields predicts risk premia in both short-term interest...

This paper proposes a general statistical framework for systemic financial stress indices which measure the severity of financial crises on a continuous scale. Several index designs from the financial stress and systemic risk literature can be represented as special cases. We introduce an...