Using Machine Learning to Estimate Multidimensional Poverty
Автор: Institute for International Economic Policy (IIEP)
Загружено: 2026-02-03
Просмотров: 24
Описание:
As part of our Spring 2025 programming, IIEP collaborated with the Oxford Poverty and Human Development Initiative (OPHI) to host a joint seminar on global multidimensional poverty. The final session featured Heriberto Tapia and Moumita Ghorai of the United Nations Development Programme (UNDP), who presented “Using Machine Learning to Estimate Multidimensional Poverty.”
The Global MPI typically relies on Demographic and Health Surveys (DHS) and Multiple Indicator Cluster Surveys (MICS); however, these sources are limited by data gaps. In this seminar, speakers from the Human Development Report Office at UNDP presented research using both daytime and nighttime satellite imagery to develop machine-learning models capable of predicting multidimensional poverty at the local, or cluster, level. The analysis shows that satellite imagery at the cluster level has strong predictive power, explaining significant variation in poverty within countries, with stronger predictive performance in rural areas than in urban areas. Overall, these findings highlight the potential of satellite imagery as a valuable tool for predicting poverty and informing policy in regions with limited ground-level survey data.
Interested in similar events? Sign up for the IIEP mailing list: http://bit.ly/IIEPsignup
Повторяем попытку...
Доступные форматы для скачивания:
Скачать видео
-
Информация по загрузке: