Adel Daoud Discusses Machine Learning Approach to Confronting Child Poverty at Pardee Center Seminar
On November 13, the Pardee Center hosted a seminar featuring Adel Daoud, a Docent/Associate Professor in Sociology at the University of Gothenburg in Sweden and a Bell Fellow at the Harvard T.H. Chan School of Public Health, where he explored the impacts of IMF programs on child poverty in low- and middle-income countries using a machine learning approach.
In his talk, Daoud explored a study he led using a sample of nearly 2 million children in 67 nations that examines the effects on child poverty of economic shocks following the implementation of International Monetary Fund (IMF) programs around the year 2000. The study uses machine learning to capture non-linear interactions between characteristics of nations and families, finding that children’s average probability of falling into poverty increased by 14 percentage points due to IMF programs. Contrary to previous analyses that emphasize the vulnerability of low-income families, the study finds that children of the middle-class face at least as high a risk of poverty as a result of economic shocks.
Watch the full seminar above.