Refugees who obtain resettlement in third countries may often face challenges integrating into host societies. This project has developed a flexible data-driven algorithm that assigns refugees across resettlement locations to improve integration outcomes. The algorithm uses a combination of supervised machine learning and optimal matching to discover and leverage synergies between refugee characteristics and resettlement sites.
The algorithm was tested on historical registry data from two countries with different assignment regimes and refugee populations, the United States and Switzerland. The approach led to an increase by roughly 40–70%, on average, in refugees’ employment rates relative to current assignment practices. Overall, this approach suggests an innovative data-driven tool to governments, one that can be implemented within existing institutional structures. It can be replicated in other contexts as well, provided the governmental framework allows for conducting this experiment.
(Image: © Muse Mohammed, IOM)