National Bureau of Economic Research

About: National Bureau of Economic Research is a nonprofit organization based out in Cambridge, Massachusetts, United States. It is known for research contribution in the topics: Monetary policy & Population. The organization has 2626 authors who have published 34177 publications receiving 2818124 citations. The organization is also known as: NBER & The National Bureau of Economic Research.

Combining satellite imagery and machine learning to predict poverty

Abstract: Reliable data on economic livelihoods remain scarce in the developing world, hampering efforts to study these outcomes and to design policies that improve them. Here we demonstrate an accurate, inexpensive, and scalable method for estimating consumption expenditure and asset wealth from high-resolution satellite imagery. Using survey and satellite data from five African countries—Nigeria, Tanzania, Uganda, Malawi, and Rwanda—we show how a convolutional neural network can be trained to identify image features that can explain up to 75% of the variation in local-level economic outcomes. Our method, which requires only publicly available data, could transform efforts to track and target poverty in developing countries. It also demonstrates how powerful machine learning techniques can be applied in a setting with limited training data, suggesting broad potential application across many scientific domains.

Capital Flow Waves: Surges, Stops, Flights and Retranchment

Abstract: This paper analyzes the drivers of international waves in capital flows. We build on the literature on “sudden stops” and “bonanzas” to develop a new methodology for identifying episodes of extreme capital flow movements using quarterly data on gross inflows and gross outflows, differentiating activity by foreigners and domestics. We identify episodes of “surge”, “stop”, “flight”, and “retrenchment” and show how our approach yields fundamentally different results than the previous literature that used measures of net flows. Global factors, especially global risk, are the most important determinants of these episodes. Contagion, especially through trade and the bilateral exposure of banking systems, is important in determining stop and retrenchment episodes. Domestic macroeconomic characteristics are generally less important, although changes in domestic economic growth influence episodes caused by foreigners. We find little role for capital controls in reducing capital flow waves. The results help provide insights for different theoretical approaches explaining crises and capital flow volatility.

Predictable Risk and Returns in Emerging Markets

Abstract: The emergence of new equity markets in Europe, Latin America, Asia, the Mideast and Africa provides a new menu of opportunities for investors. These markets exhibit high expected returns as well as high volatility. Importantly, the low correlations with developed countries' equity markets significantly reduces the unconditional portfolio risk of a world investor. However, standard global asset pricing models, which assume complete integration of capital markets, fail to explain the cross section of average returns in emerging countries. An analysis of the predictability of the returns reveals that emerging market returns are more likely than developed countries to be influenced by local information. Article published by Oxford University Press on behalf of the Society for Financial Studies in its journal, The Review of Financial Studies.