Forecasting Fiscal Crises in Emerging Markets and Low-Income Countries with Machine Learning Models

Pre-existing public debt vulnerabilities have been exacerbated by the effects of the pandemic, raising the risk of fiscal crises in emerging and low-income countries. This underscores the importance of models aimed at capturing the main determinants of fiscal distress episodes and forecasting the occurrence of sovereign debt crises. In this regard, our paper shows that ensemble tree methods, in particular random forests, are able to outperform standard econometric approaches, such as the probit model. This over-performance is not limited to short-term forecasting horizons, as documented by the previous literature, but holds also at longer horizons. The analysis also identifies the variables that are the most relevant predictors of fiscal crises at different forecasting horizons and provides an assessment of their impact on the probability of observing a crisis episode. Finally, the forecasts of the best performing machine learning algorithm are used to derive aggregate fiscal distress indexes that are able to signal effectively the build-up of debt-related vulnerabilities in emerging and low-income countries.