Placement optimization in refugee resettlement
Every year tens of thousands of refugees are resettled to dozens of host countries. 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 decisions. We integrate machine learnin...
| Главные авторы: | , , , , |
|---|---|
| Формат: | Journal article |
| Язык: | English |
| Опубликовано: |
INFORMS
2021
|
| _version_ | 1826290632415510528 |
|---|---|
| author | Ahani, N Andersson, T Martinello, A Teytelboym, A Trapp, A |
| author_facet | Ahani, N Andersson, T Martinello, A Teytelboym, A Trapp, A |
| author_sort | Ahani, N |
| collection | OXFORD |
| description | Every year tens of thousands of refugees are resettled to dozens of host countries. 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 decisions. We integrate machine learning and integer optimization into an innovative software tool, Annie Moore, that assists a US resettlement agency with matching refugees to their initial placements. Our software suggests optimal placements while giving substantial autonomy to the resettlement staff to finetune recommended matches, thereby streamlining their resettlement operations. Initial backtesting indicates that Annie can improve short-run employment outcomes by 22%–38%. We conclude by
discussing several directions for future work. |
| first_indexed | 2024-03-07T02:47:10Z |
| format | Journal article |
| id | oxford-uuid:ac6d7b8d-203e-4fd8-9bb7-cf9f8735bb87 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T02:47:10Z |
| publishDate | 2021 |
| publisher | INFORMS |
| record_format | dspace |
| spelling | oxford-uuid:ac6d7b8d-203e-4fd8-9bb7-cf9f8735bb872022-03-27T03:29:00ZPlacement optimization in refugee resettlementJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:ac6d7b8d-203e-4fd8-9bb7-cf9f8735bb87EnglishSymplectic ElementsINFORMS2021Ahani, NAndersson, TMartinello, ATeytelboym, ATrapp, AEvery year tens of thousands of refugees are resettled to dozens of host countries. 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 decisions. We integrate machine learning and integer optimization into an innovative software tool, Annie Moore, that assists a US resettlement agency with matching refugees to their initial placements. Our software suggests optimal placements while giving substantial autonomy to the resettlement staff to finetune recommended matches, thereby streamlining their resettlement operations. Initial backtesting indicates that Annie can improve short-run employment outcomes by 22%–38%. We conclude by discussing several directions for future work. |
| spellingShingle | Ahani, N Andersson, T Martinello, A Teytelboym, A Trapp, A Placement optimization in refugee resettlement |
| title | Placement optimization in refugee resettlement |
| title_full | Placement optimization in refugee resettlement |
| title_fullStr | Placement optimization in refugee resettlement |
| title_full_unstemmed | Placement optimization in refugee resettlement |
| title_short | Placement optimization in refugee resettlement |
| title_sort | placement optimization in refugee resettlement |
| work_keys_str_mv | AT ahanin placementoptimizationinrefugeeresettlement AT anderssont placementoptimizationinrefugeeresettlement AT martinelloa placementoptimizationinrefugeeresettlement AT teytelboyma placementoptimizationinrefugeeresettlement AT trappa placementoptimizationinrefugeeresettlement |