The study used machine learning to assess consumer spending and asset wealth, using high-resolution satellite imagery to measure poverty in Africa.
According to the project website, "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 this study demonstrates 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—the study shows 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. This 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." https://science.sciencemag.org/content/353/6301/790
Machine learning methods could supplement traditional efforts to track and target poverty in developing countries.