Consider two views of the global financial crisis. One view looks across the border: it blames external imbalances, the unprecedented current account deficits and surpluses in recent years. Another view looks within the border: it faults domestic financial systems where risks originated in...

This paper shows how the role of Financial Soundness Indicators (FSIs) in financial surveillance can be usefully enhanced. Drawing from different statistical techniques, the paper illustrates that FSIs generate signals that can accurately detect, with 4 to 12 quarters lead, emerging financial...

Forecasting macroeconomic variables is key to developing a view on a country's economic outlook.Most traditional forecasting models rely on fitting data to a pre-specified relationship between inputand output variables, thereby assuming a specific functional and stochastic process underlying...

We develop a framework to nowcast (and forecast) economic variables with machine learning techniques. We explain how machine learning methods can address common shortcomings of traditional OLS-based models and use several machine learning models to predict real output growth with lower forecast...

This paper describes recent work to strengthen nowcasting capacity at the IMF’s European department. It motivates and compiles datasets of standard and nontraditional variables, such as Google search and air quality. It applies standard dynamic factor models (DFMs) and several machine learning...

We produce a social unrest risk index for 125 countries covering a period of 1996 to 2020. The risk of social unrest is based on the probability of unrest in the following year derived from a machine learning model drawing on over 340 indicators covering a wide range of macro-financial,...

In this paper I assess the ability of econometric and machine learning techniques to predict fiscal crises out of sample. I show that the econometric approaches used in many policy applications cannot outperform a simple heuristic rule of thumb. Machine learning techniques (elastic net, random...

Machine learning models are becoming increasingly important in the prediction of economic crises. The models, however, use datasets comprising a large number of predictors (features) which impairs model interpretability and their ability to provide adequate guidance in the design of crisis...

We develop an empirical model to predict banking crises in a sample of 60 low-incomecountries (LICs) over the 1981-2015 period. Given the recent emergence of financial sectorstress associated with low commodity prices in several LICs, we assign price movements inprimary commodities a key role in...

This paper updates the database on systemic banking crises presented in Laeven and Valencia (2008, 2013). Drawing on 151 systemic banking crises episodes around the globe during 1970-2017, the database includes information on crisis dates, policy responses to resolve banking crises, and the...