We leverage insights from machine learning to optimize the trade off between bias and variance when estimating economic models using pooled datasets. Specifically, we develop a simple algorithm that estimates the similarity of economic structures across countries and selects the optimal pool of...

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...

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 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,...

We introduce unFEAR, Unsupervised Feature Extraction Clustering, to identify economic crisis regimes. Given labeled crisis and non-crisis episodes and the corresponding features values, unFEAR uses unsupervised representation learning and a novel mode contrastive autoencoder to group episodes...

The central counterparties dominating the market for the clearing of over-the-counter interest rate and credit derivatives are globally systemic. Employing methodologies similar to the calculation of banks' capital requirements against trading book exposures, this paper assesses the sensitivity...

The central counterparties dominating the market for the clearing of over-the-counter interest rate and credit derivatives are globally systemic. Employing methodologies similar to the calculation of banks' capital requirements against trading book exposures, this paper assesses the sensitivity...

The global financial crisis has placed the spotlight squarely on bank stress tests. Stress tests conducted in the lead-up to the crisis, including those by IMF staff, were not always able to identify the right risks and vulnerabilities. Since then, IMF staff has developed more robust stress...

Bank liquidity stress testing, which has become de rigueur following the costly lessons of the global financial crisis, remains underdeveloped compared to solvency stress testing. The ability to adequately identify, model and assess the impact of liquidity shocks, which are infrequent but can...

Recent advances in digital technology and big data have allowed FinTech (financial technology)lending to emerge as a potentially promising solution to reduce the cost of credit and increasefinancial inclusion. However, machine learning (ML) methods that lie at the heart of FinTech credithave...