Placement Optimization in Refugee Resettlement
(2021) In Operations Research 69(5). p.1468-1486- Abstract
- Every year, tens of thousands of refugees are resettled to dozens of host countries. Although there is growing evidence that the initial placement of refugee families profoundly affects their lifetime outcomes, there have been few attempts to optimize resettlement decisions. We integrate machine learning and integer optimization into an innovative software tool, Annie™ Matching and Outcome Optimization for Refugee Empowerment (Annie™ Moore), that assists a U.S. resettlement agency with matching refugees to their initial placements. Our software suggests optimal placements while giving substantial autonomy to the resettlement staff to fine-tune recommended matches, thereby streamlining their resettlement operations. Initial back testing... (More)
- Every year, tens of thousands of refugees are resettled to dozens of host countries. Although there is growing evidence that the initial placement of refugee families profoundly affects their lifetime outcomes, there have been few attempts to optimize resettlement decisions. We integrate machine learning and integer optimization into an innovative software tool, Annie™ Matching and Outcome Optimization for Refugee Empowerment (Annie™ Moore), that assists a U.S. resettlement agency with matching refugees to their initial placements. Our software suggests optimal placements while giving substantial autonomy to the resettlement staff to fine-tune recommended matches, thereby streamlining their resettlement operations. Initial back testing indicates that Annie™ can improve short-run employment outcomes by 22%–38%. We conclude by discussing several directions for future work. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/c74d915b-3385-474d-9b96-8b781e98a28c
- author
- Ahani, Narges ; Andersson, Tommy LU ; Martinello, Alessandro LU ; Teytelboym, Alexander and Trapp, Andrew C.
- organization
- publishing date
- 2021-03-24
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- refugee resettlement, matching, integer optimization, machine learning, humanitarian operations
- in
- Operations Research
- volume
- 69
- issue
- 5
- pages
- 1468 - 1486
- publisher
- Inst Operations Research Management Sciences
- external identifiers
-
- scopus:85113147158
- ISSN
- 0030-364X
- DOI
- 10.1287/opre.2020.2093
- language
- English
- LU publication?
- yes
- id
- c74d915b-3385-474d-9b96-8b781e98a28c
- date added to LUP
- 2021-05-12 14:24:53
- date last changed
- 2022-04-27 01:57:12
@article{c74d915b-3385-474d-9b96-8b781e98a28c, abstract = {{Every year, tens of thousands of refugees are resettled to dozens of host countries. Although there is growing evidence that the initial placement of refugee families profoundly affects their lifetime outcomes, there have been few attempts to optimize resettlement decisions. We integrate machine learning and integer optimization into an innovative software tool, Annie™ Matching and Outcome Optimization for Refugee Empowerment (Annie™ Moore), that assists a U.S. resettlement agency with matching refugees to their initial placements. Our software suggests optimal placements while giving substantial autonomy to the resettlement staff to fine-tune recommended matches, thereby streamlining their resettlement operations. Initial back testing indicates that Annie™ can improve short-run employment outcomes by 22%–38%. We conclude by discussing several directions for future work.}}, author = {{Ahani, Narges and Andersson, Tommy and Martinello, Alessandro and Teytelboym, Alexander and Trapp, Andrew C.}}, issn = {{0030-364X}}, keywords = {{refugee resettlement; matching; integer optimization; machine learning; humanitarian operations}}, language = {{eng}}, month = {{03}}, number = {{5}}, pages = {{1468--1486}}, publisher = {{Inst Operations Research Management Sciences}}, series = {{Operations Research}}, title = {{Placement Optimization in Refugee Resettlement}}, url = {{http://dx.doi.org/10.1287/opre.2020.2093}}, doi = {{10.1287/opre.2020.2093}}, volume = {{69}}, year = {{2021}}, }