machine learning

Mapping the dimensions of poverty through big data, socioeconomic surveys and machine learning in Cambodia

Up-to-date poverty data are scarce in Cambodia. We combine household surveys with satellite data, such as nighttime lights, and machine learning to map, down to the household level, where people lack basics like clean water, sanitation, electricity, and education.

Lack of Global Convergence and the Formation of Multiple Welfare Clubs across Countries: An Unsupervised Machine Learning Approach

The paper incorporates some recent developments from the unsupervised machine learning literature to re-evaluate the cross-country convergence hypothesis in a context beyond GDP. The application of a distribution-based clustering algorithm suggests the formation of three local convergence clubs.