Improving refugee integration through data-driven algorithmic assignment. Bansak, K., Ferwerda, J., Hainmueller, J., Dillon, A., Hangartner, D., Lawrence, D., & Weinstein, J. Science, 359(6373):325–329, January, 2018. ![Improving refugee integration through data-driven algorithmic assignment [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex 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. 325 Developed democracies are settling an increased number of refugees, many of whom face challenges integrating into host societies. We 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. Our approach led to gains of roughly 40 to 70%, on average, in refugees’ employment outcomes relative to current assignment practices. This approach can provide governments with a practical and cost-efficient policy tool that can be immediately implemented within existing institutional structures. A machine learning–based algorithm for assigning refugees can improve their employment prospects over current approaches. A machine learning–based algorithm for assigning refugees can improve their employment prospects over current approaches.
@article{bansak_improving_2018,
title = {Improving refugee integration through data-driven algorithmic assignment},
volume = {359},
copyright = {Copyright © 2018 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. http://www.sciencemag.org/about/science-licenses-journal-article-reuseThis is an article distributed under the terms of the Science Journals Default License.},
issn = {0036-8075, 1095-9203},
url = {https://science.sciencemag.org/content/359/6373/325},
doi = {10.1126/science.aao4408},
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. 325
Developed democracies are settling an increased number of refugees, many of whom face challenges integrating into host societies. We 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. Our approach led to gains of roughly 40 to 70\%, on average, in refugees’ employment outcomes relative to current assignment practices. This approach can provide governments with a practical and cost-efficient policy tool that can be immediately implemented within existing institutional structures.
A machine learning–based algorithm for assigning refugees can improve their employment prospects over current approaches.
A machine learning–based algorithm for assigning refugees can improve their employment prospects over current approaches.},
language = {en},
number = {6373},
urldate = {2020-08-05},
journal = {Science},
author = {Bansak, Kirk and Ferwerda, Jeremy and Hainmueller, Jens and Dillon, Andrea and Hangartner, Dominik and Lawrence, Duncan and Weinstein, Jeremy},
month = jan,
year = {2018},
pmid = {29348237},
pages = {325--329},
}
Downloads: 0
{"_id":"EMB323wXSMvfAFfXT","bibbaseid":"bansak-ferwerda-hainmueller-dillon-hangartner-lawrence-weinstein-improvingrefugeeintegrationthroughdatadrivenalgorithmicassignment-2018","authorIDs":[],"author_short":["Bansak, K.","Ferwerda, J.","Hainmueller, J.","Dillon, A.","Hangartner, D.","Lawrence, D.","Weinstein, J."],"bibdata":{"bibtype":"article","type":"article","title":"Improving refugee integration through data-driven algorithmic assignment","volume":"359","copyright":"Copyright © 2018 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. http://www.sciencemag.org/about/science-licenses-journal-article-reuseThis is an article distributed under the terms of the Science Journals Default License.","issn":"0036-8075, 1095-9203","url":"https://science.sciencemag.org/content/359/6373/325","doi":"10.1126/science.aao4408","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. 325 Developed democracies are settling an increased number of refugees, many of whom face challenges integrating into host societies. We 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. Our approach led to gains of roughly 40 to 70%, on average, in refugees’ employment outcomes relative to current assignment practices. This approach can provide governments with a practical and cost-efficient policy tool that can be immediately implemented within existing institutional structures. A machine learning–based algorithm for assigning refugees can improve their employment prospects over current approaches. A machine learning–based algorithm for assigning refugees can improve their employment prospects over current approaches.","language":"en","number":"6373","urldate":"2020-08-05","journal":"Science","author":[{"propositions":[],"lastnames":["Bansak"],"firstnames":["Kirk"],"suffixes":[]},{"propositions":[],"lastnames":["Ferwerda"],"firstnames":["Jeremy"],"suffixes":[]},{"propositions":[],"lastnames":["Hainmueller"],"firstnames":["Jens"],"suffixes":[]},{"propositions":[],"lastnames":["Dillon"],"firstnames":["Andrea"],"suffixes":[]},{"propositions":[],"lastnames":["Hangartner"],"firstnames":["Dominik"],"suffixes":[]},{"propositions":[],"lastnames":["Lawrence"],"firstnames":["Duncan"],"suffixes":[]},{"propositions":[],"lastnames":["Weinstein"],"firstnames":["Jeremy"],"suffixes":[]}],"month":"January","year":"2018","pmid":"29348237","pages":"325–329","bibtex":"@article{bansak_improving_2018,\n\ttitle = {Improving refugee integration through data-driven algorithmic assignment},\n\tvolume = {359},\n\tcopyright = {Copyright © 2018 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. http://www.sciencemag.org/about/science-licenses-journal-article-reuseThis is an article distributed under the terms of the Science Journals Default License.},\n\tissn = {0036-8075, 1095-9203},\n\turl = {https://science.sciencemag.org/content/359/6373/325},\n\tdoi = {10.1126/science.aao4408},\n\tabstract = {Data-driven refugee assignment\nThe 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\\%.\nScience, this issue p. 325\nDeveloped democracies are settling an increased number of refugees, many of whom face challenges integrating into host societies. We 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. Our approach led to gains of roughly 40 to 70\\%, on average, in refugees’ employment outcomes relative to current assignment practices. This approach can provide governments with a practical and cost-efficient policy tool that can be immediately implemented within existing institutional structures.\nA machine learning–based algorithm for assigning refugees can improve their employment prospects over current approaches.\nA machine learning–based algorithm for assigning refugees can improve their employment prospects over current approaches.},\n\tlanguage = {en},\n\tnumber = {6373},\n\turldate = {2020-08-05},\n\tjournal = {Science},\n\tauthor = {Bansak, Kirk and Ferwerda, Jeremy and Hainmueller, Jens and Dillon, Andrea and Hangartner, Dominik and Lawrence, Duncan and Weinstein, Jeremy},\n\tmonth = jan,\n\tyear = {2018},\n\tpmid = {29348237},\n\tpages = {325--329},\n}\n\n","author_short":["Bansak, K.","Ferwerda, J.","Hainmueller, J.","Dillon, A.","Hangartner, D.","Lawrence, D.","Weinstein, J."],"key":"bansak_improving_2018","id":"bansak_improving_2018","bibbaseid":"bansak-ferwerda-hainmueller-dillon-hangartner-lawrence-weinstein-improvingrefugeeintegrationthroughdatadrivenalgorithmicassignment-2018","role":"author","urls":{"Paper":"https://science.sciencemag.org/content/359/6373/325"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"http://bibbase.org/zotero-group/russellneal/2540015","creationDate":"2020-10-15T07:56:08.142Z","downloads":0,"keywords":[],"search_terms":["improving","refugee","integration","through","data","driven","algorithmic","assignment","bansak","ferwerda","hainmueller","dillon","hangartner","lawrence","weinstein"],"title":"Improving refugee integration through data-driven algorithmic assignment","year":2018,"dataSources":["ng5gEGPt3irNQcwtE"]}