Using AI to target aid in Togo

Podcast

Speaker(s)

Joshua Blumenstock

Assistant Professor, School of Information, UC Berkeley, Director, Data-Intensive Development Lab, UC Berkeley , Director, Global Policy Lab, UC Berkeley, Faculty Co-Director, Center for Effective Global Action, UC Berkeley

BIDS Faculty Council Member Joshua Blumenstock is an Assistant Professor at the UC Berkeley School of Information, the Director of the Data-Intensive Development Lab and the Global Policy Lab, and the Faculty Co-Director of the Center for Effective Global Action. His research lies at the intersection of machine learning and development economics, and focuses on using novel data and methods to better understand the causes and consequences of global poverty.  Joshua has a PhD in Information Science and a MA in Economics from UC Berkeley, and Bachelor’s degrees in Computer Science and Physics from Wesleyan University.  He is a recipient of the Intel Faculty Early Career Honor, a Gates Millennium Grand Challenge award, a Google Faculty Research Award, and the U.C. Berkeley Chancellor's Award for Public Service. His work has appeared in a variety of publications including Science, Nature, the American Economic Review, and the proceedings of KDD, NeurIPS, and AAAI.

Friday, October 1, 2021

There is often an urgent need for humanitarian assistance in low-income countries. But how can it be targeted efficiently and quickly?

In this recent VoxEU Economics podcast interview, BIDS Faculty Affiliate Joshua Blumenstock tells Tim Phillips how, in Togo, a combination of machine learning and mobile phone data dramatically increased the effectiveness of Covid assistance. 

Read more about the research discussed and download the free discussion paper: Machine Learning and Mobile Phone Data Can Improve the Targeting of Humanitarian Assistance (Aiken, E, Bellue, S, Blumenstock, J, Karlan, D and Udry, C. 2021. CEPR.).

 

Share this video