World Data Lab specializes in creating economic and demographic models that help organizations make data-driven decisions. Our global team of data scientists, economists, demographers, and developers are passionate about combining new data sources with groundbreaking methods to push the frontiers of what is knowable.
Several countries in the world pose particular challenges to the development community. Due to war or political considerations, little can be said regarding conditions on the ground or where aid and other support could best be deployed. World Data Lab is pioneering new approaches to solve this challenge. Using hybrid techniques in data sourcing and modeling, we can develop reliable subnational poverty estimates for challenging environments.
This model estimates poverty and income in all of North Korea’s provinces. The model uses satellite nightlight luminosity data to infer economic power by comparing the luminosity of North Korea’s regions to the luminosity levels of rural Chinese areas. It imputes income distribution by matching census data to similar countries with more data. This is based on age pyramids, sectoral employment structure, education structure, and our GDP estimates.
World Data Lab's pioneering methods drove the collaborative* 18-month research project featured in The Economist: "When the lights go out: Satellite Data Shed New Light on North Korea’s Opaque Economy”**. The article explores frontier methods for estimating economic activity and poverty dynamics in environments with little-to-no pre-existing baseline data. This short FAQ answers several key questions about the research and its outcomes.
*This research project was led and coordinated by World Data Lab (WDL), who worked in close partnership with the Vienna University of Economics and Business (WU) and the International Institute for Applied Systems Analysis (IIASA). The NOMIS Foundation provided funding for the development and execution of this research project.
**From The Economist, 4th May 2019 © The Economist Newspaper Limited, London. All rights reserved.
We are interested in applying these pioneering techniques to other environments where little is known but needs are particularly great. Partner with us to learn more about how we can collaborate.