This advertisement is for one to two postdoc positions on using machine learning and causal inference to evaluate the impact of local development programs in Africa. The candidate will work as part of an interdisciplinary team towards the goals of Observatory of Poverty project which is situated at the AI and Global Development Lab (you will find more information about the Lab at (global-lab.ai) and The Institute for Analytical Sociology (IAS). The vision of the Lab is to “combine AI, earth observation, and socio-economic theories to analyze sustainable and human development globally.” The Lab is mainly located at DSAI and IAS.
About the project
About 900 million people—one-third in Africa—live in extreme poverty. Operating on the assumption that life in impoverished communities is fundamentally so different that it can trap people in cycles of deprivation (‘poverty traps’), major development agencies have deployed a stream of development projects to break these cycles (‘poverty targeting’). However, scholars are currently unable to answer questions such as in what capacity do poverty traps exist; to what extent do these interventions release communities from such traps—as they are held back by a data challenges. This challenge is that there is a lack of geo-temporal poverty data, and thus, one of the goals of the Observatory of Poverty project is to develop new methods to produce such data. As this challenge is already being handled by our team at the AI and Global Development Lab, the prospective candidate will join the Lab to use these data for evaluating the effect of local development programs, using a causal-inference design.
Thus, the candidate will contribute to the following goal: to use our data to identify to what extent African communities are trapped in poverty and explain how competing development interventions alter these communities’ prospects to free themselves from deprivation. To achieve this goal, the project will tackle the following objectives:
To examine how World Bank (WB) development programs versus Chinese programs, select African communities, and how these affect communities’ chances of breaking the cycle of deprivation (using the data of Obj1).
To develop theories of the varieties of poverty traps by examining the extent to which these traps lurk in different social contexts that shape both local governance and public-service provisioning, and how these contexts may be more or less important for Chinese- or WB-styled projects.
Please be sure to indicate that you saw this position on Globaljobs.org