Skip to Main Navigation

Machine Learning and the Future of Poverty Prediction

February 27, 2018

Washington, DC and Online

  • Measuring poverty is notoriously difficult. The collection of detailed data on households is time-consuming and expensive. But the marriage of machine learning techniques to lighter collection instruments may transform how the World Bank and its development partners approach poverty measurement. Predicting a household’s poverty status with a handful of easy-to-collect qualitative variables lowers costs, decreases turnaround times, and, ultimately, creates a more solid empirical foundation for policy.

    Poverty prediction typically relies on regression models. In this talk, Olivier Dupriez will report on a comparative assessment of machine learning classification algorithms applied to poverty prediction. He will discuss preliminary outcomes of three approaches to build predictive models: crowd-sourcing via a data-science competition that already has 1,500+ data scientists working to develop the best poverty prediction model for three countries; contracting experts; and exploiting some of the newest approaches such as automated machine learning for model development.

    In addition, Olivier will also discuss his work to apply machine learning to the Bank’s own knowledge base by automatically extracting topics from 145,000 documents published in the Bank’s Documents and Reports repository. This project aims to improve data and knowledge discovery systems. The application of natural language processing tools is also useful in showing how the coverage of various topics such as agriculture, energy, health, climate change, and others have evolved over time, across regions, and differ by type of document.

  • Image

    Olivier Dupriez

    Lead Statistician

    Olivier Dupriez is a Lead Statistician in the Development Data Group. He leads a team in charge of the World Bank’s Microdata Library, and is the learning and innovation coordinator for the data group. His current interests include research and applied work in statistical disclosure control, machine learning, synthetic data and dynamic micro-simulation, and the analysis of household consumption patterns.


    Asli Demirgüç-Kunt

    Director of Research

    Asli Demirgüç-Kunt is the Director of Research in the World Bank. After joining the Bank in 1989 as a Young Economist, she has held different positions, including Director of Development Policy, Chief Economist of Financial and Private Sector Development Network, and Senior Research Manager, doing research and advising on financial sector and private sector development issues.

    Carolina Sanchez

    Senior Director, Poverty

    Carolina Sanchez, a Spanish national, is currently the Senior Director of the Poverty and Equity Global Practice (GP) at the World Bank. Prior to this assignment, she was the Poverty and Equity GP Practice Manager in the Europe and Central Asia region. Carolina has worked on operations, policy advice and analytical activities in Eastern Europe, Latin America and South Asia, and was part of the core team working on the WDR2012, “Gender Equality and Development”.

  • The Policy Research Talks showcase the latest findings of the research department and their implications for World Bank operations. The monthly event facilitates a dialogue between researchers and operational staff so that we can challenge and contribute to the World Bank's intellectual climate and re-examine conventional wisdom in current development theories and practices. Read More »


  • Time: 3:00 - 4:30 PM
  • Location: MC 13-121, World Bank Main Complex