Tommy Andersson
Professor
Refugee resettlement via machine learning and integer optimization
Author
Editor
- Ahmed Kheiri
Summary, in English
Around 100,000 refugees are resettled to dozens of countries from conflict zones every year. While there is growing evidence that the initial placement of refugee families profoundly affects their lifetime outcomes, there have been few attempts to optimize resettlement destinations within host countries. We describe how machine learning and integer optimization can be used to empower resettlement agencies to drastically improve refugee employment outcomes. We describe possible future work on multi-objective optimization, the dynamics of allocation, and the inclusion of refugee preferences.
Department/s
- Department of Economics
Publishing year
2018
Language
English
Pages
21-26
Publication/Series
OR60 : The OR Society Annual Conference
Document type
Conference paper
Publisher
OR Society
Topic
- Political Science (excluding Public Administration Studies and Globalization Studies)
- Information Systems
Keywords
- Humanitarian operations research
- Integer optimization
- Machine learning
- Matching
- Multiple multidimensional knapsack problem
- Refugees
Conference name
60th Annual Conference of the Operational Research Society, OR 2018
Conference date
2018-09-11 - 2018-09-13
Conference place
Lancaster, United Kingdom
Status
Published
ISBN/ISSN/Other
- ISBN: 9780903440646