Improving refugee integration through data-driven algorithmic assignment
- 19 January 2018
- journal article
- research article
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 359 (6373) , 325-329
Abstract
Data-driven refugee assignment: The continuing refugee crisis has made it necessary for governments to find ways to resettle individuals and families in host communities. Bansak et al. used a machine learning approach to develop an algorithm for geographically placing refugees to optimize their overall employment rate. The authors developed and tested the algorithm on segments of registry data from the United States and Switzerland. The algorithm improved the employment prospects of refugees in the United States by ∼40% and in Switzerland by ∼75%. Science , this issue p. 325Keywords
Funding Information
- Ford Foundation
- Carnegie Corporation of New York
This publication has 23 references indexed in Scilit:
- When lives are put on hold: Lengthy asylum processes decrease employment among refugeesScience Advances, 2016
- Borders and migration: an issue of global health importanceThe Lancet Global Health, 2016
- Tradable Refugee-admission Quotas and EU Asylum PolicyCESifo Economic Studies, 2014
- Tradable immigration quotasJournal of Public Economics, 2014
- Social Networks and the Dynamics of Labour Market Outcomes: Evidence from Refugees Resettled in the U.S.Review of Economic Studies, 2011
- Explaining the Refugee Gap: Economic Outcomes of Refugees versus Other ImmigrantsJournal of Refugee Studies, 2010
- Ethnic Enclaves and Immigrant Labor Market Outcomes: Quasi‐Experimental EvidenceJournal of Labor Economics, 2009
- Optimal Full Matching and Related Designs via Network FlowsJournal of Computational and Graphical Statistics, 2006
- Ethnic Enclaves and the Economic Success of Immigrants--Evidence from a Natural ExperimentThe Quarterly Journal of Economics, 2003
- Greedy function approximation: A gradient boosting machine.The Annals of Statistics, 2001