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 errors than traditional models. By combining multiple machine learning models into ensembles, we lower forecast errors even further. We also identify measures of variable importance to help improve the transparency of machine learning-based forecasts. Applying the framework to Turkey reduces forecast errors by at least 30 percent relative to traditional models. The framework also better predicts economic volatility, suggesting that machine learning techniques could be an important part of the macro forecasting toolkit of many countries.
We leverage insights from machine learning to optimize the tradeoff 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 countries to maximize out-of-sample prediction accuracy of a model. We apply the new alogrithm by nowcasting output growth with a panel of 102 countries and are able to significantly improve forecast accuracy relative to alternative pools. The algortihm improves nowcast performance for advanced economies, as well as emerging market and developing economies, suggesting that machine learning techniques using pooled data could be an important macro tool for many countries.
This paper studies the potential effects of geoeconomic fragmentation (GEF) in the sub-Saharan Africa region (SSA) through quantifying potential long-term economic costs. The paper considers two alternative GEF scenarios in which trade relations are fully or partially curtailed across world economies. Our quantification relies on a multi-country multi-sector general equilibrium model and takes a deep dive into the impact across SSA’s oil-rich, other resource-rich and non-resource-rich countries. The results are based on a detailed dataset including information for 136 tradable primary commodity and 24 manufacturing and services sectors in 145 countries—32 of which are in SSA. We find that under GEF, SSA could experience long-term wellfare losses of approximately 4 percent of GDP, twice the losses of the rest of the world. This strong effect results from the large losses of other resource-rich and non-resource rich countries in SSA, given their high dependence on commodity trade. However, if the world experiences a less severe GEF-induced trade disruption—a strategic decoupling—SSA countries could derive minor gains from the re-shuffling of global market supply, specially in energy products.
The Covid-19 pandemic has led to a large disruption of global supply chains. This paper studies the implications of supply chain disruptions for inflation and monetary policy in sub-Saharan Africa. Increases in supply chain pressures have had a sizeable impact on headline, food, and tradable inflation for a panel of 29 sub-Saharan African countries from 2000 to 2022. Our findings suggest that central banks can stabilize inflation and output more efficiently by monitoring global supply chains and adjusting the monetary policy stance before the disruptions have fully passed through into all inflation components. The gains from monitoring supply chain disruptions are particularly large for open economies which tend to experience outsized second-round effects on the prices of non-tradable goods and services.
We construct a new database which covers production and trade in 136 primary commodities and 24 manufacturing and service sectors for 145 countries. Using this new more granular data, we estimate spillover effects from plausible trade fragmentation scenarios in a new multi-country, multi-sector, general-equilibrium model that accounts for unique demand and supply characteristics of commodities. The results show fragmentation-induced output losses can be sizable, especially for Low-Income-Countries, although the magnitudes vary according to the particular scenarios and modelling assumptions. Our work demonstrates that not accounting for granular commodity production and trade linkages leads to underestimation of the output losses associated with trade fragmentation.
Rising debt vulnerabilities in low- and middle-income countries have rekindled interest in a Brady Plan-style mechanism to facilitate debt restructurings. To inform this debate, this paper analyzes the impact of the original Brady Plan by comparing macroeconomic outcomes of 10 Brady countries to 40 other emerging markets and developing economies. The paper finds that following the first Brady restructuring in 1990, Brady countries experienced substantial declines in public and external debt burdens and a sharp pick-up in output and productivity growth, anchored by a comparatively strong structural reform effort. The impact of the Brady Plan on overall debt burdens was many times greater than initial face value reductions, indicating the existence of a “Brady multiplier.” Brady restructurings took longer to complete than non-Brady restructurings. Today, similar mechanisms could be helpful in delivering meaningful debt stock reduction when solvency challenges are acute, but Brady-style mechanisms alone would not solve existing challenges in the sovereign debt landscape, including those related to creditor coordination, domestic barriers to economic reforms, and the increased prevalence of domestic debt, among others.
This will help us customize your experience to showcase the most relevant content to your age group
Please select from below
Login
Not registered?
Sign up
Already registered?
Success – Your message will goes here
We'd love to hear from you!
Thank you for visiting our website. Would you like to provide feedback on how we could improve your experience?
This site does not use any third party cookies with one exception — it uses cookies from Google to deliver its services and to analyze traffic.Learn More.