This study paired census microdata from 10 countries in Sub-Saharan Africa with additional datasets, providing information on geographic specifics such as precipitation. In doing so, the team developed models for internal and international migration flows within and across the countries, including key drivers that reflect changing social, demographic, economic and environmental landscapes. Next to measuring migration, this approach also sought to contribute to evidence-based interventions for disease control policy, economic development, and resource allocation.
The study assesses how well models can both explain and predict migration, using census microdata linked with spatial datasets. The results show that the models can explain up to 87 percent of internal migration, can predict future within-country migration with correlations of up to 0.91, and can also predict migration in other countries with correlations of up to 0.72. Overall, these findings show that such innovative data methodologies are useful tools for understanding migration as well as predicting flows, in particular in regions where data are sparse. Potentially, it can be replicated with other countries, and contribute to evidence-based interventions in strategic economic development, planning, and disease control targeting.