Assistant Professor of Economics Linden McBride Published in the journal Applied Economics Perspectives and Policy

Submitted by Michael Bruckler on July 21, 2021 - 8:42 am
July 21, 2021
By Michael Bruckler

Assistant Professor of Economics Linden McBride is lead author of the paper “Predicting Poverty and Malnutrition for Targeting, Mapping, Monitoring, and Early Warning” recently published in the journal Applied Economics Perspectives and Policy.

Increasingly plentiful data and powerful predictive algorithms heighten the promise of data science for humanitarian and development programming. McBride and her co-authors advocate for embrace of, and investment in, machine learning methods for poverty and malnutrition targeting, mapping, monitoring, and early warning while also cautioning that distinct objectives require distinct data and methods. In particular, they highlight the differences between poverty and malnutrition targeting and mapping, the differences between structural and stochastic deprivation, and the modeling and data challenges of early warning system development. Overall, they urge careful consideration of the purpose and use cases of machine learning informed models.

The paper is part of a USAID funded project titled, “Innovations in Feed the Future Monitoring and Evaluation - Harnessing Big Data and Machine Learning to Feed the Future.” All data and written products are solely the authors’ responsibility and do not necessarily reflect the views of USAID or the United States Government.

McBride’s co-authors are: Christopher B. Barrett (Cornell University), Christopher Browne (Cornell University), Leiqiu Hu (University of Alabama - Huntsville), Yanyan Liu (IFPRI), David S. Matteson (Cornell University), Ying Sun (Cornell University), and Jiaming Wen (Cornell University).

The paper is published here: https://onlinelibrary.wiley.com/doi/10.1002/aepp.13175 and an ungated version can be accessed here: https://onlinelibrary.wiley.com/share/author/TKGG3QEESIUFMJDSXTGU?target=10.1002/aepp.13175

 

 

Related