Annie™ MOORE in action
The team developed Annie™ MOORE using machine learning methods to assess the quality of a match between a refugee family and a locality based on the probability of employment for the newly arrived refugee. Using data from HIAS, the researchers discovered that if Annie™ MOORE had been used on the 496 refugees the agency resettled during 2017, the percentage of refugees gaining employment within a 90-day period would have increased somewhere between 22% and 38%.
The software was rolled out at HIAS in 2018 and has gone on to match these predictions, with early results increasing the likelihood of employment by at least 20%. Annie™ MOORE has since helped resettle over 1,000 refugees in the US. It has played a key part in eliminating mismatch between refugees and the services provided within communities, such as single parent support and language services.
Additionally, Annie™ MOORE has helped HIAS streamline and improve services. The software allows HIAS workers to spend less time on matching conventional cases, so they can focus on families with additional needs.
HIAS is in conversation with other resettlement agencies in the US about adoption of Annie™ MOORE. Meanwhile, the researchers are in discussions with other bodies around the world, including the UK Home Office, about the potential use of the software in their own jurisdictions.
Alex Teytelboym was Highly Commended in the Policy Engagement category at the 2020 Vice-Chancellor’s Innovation Awards for his work on Annie™ MOORE.
Visit Refugees.AI
References
Delacrétaz, D., S. Duke Kominers and A. Teytelboym (2019)
“Matching Mechanisms for Refugee Resettlement”
Jones, W. and A. Teytelboym (2018), “The local refugee match: Aligning refugees' preferences with the capacities and priorities of localities”, Journal of Refugee Studies.
Nguyen, H., T Nguyen and A Teytelboym (2019). “Stability in Matching Markets with Complex Constraints”
Trapp, A.C., A. Teytelboym, A. Martinello, T.Andersson and N. Ahani (2018) “Placement Optimization in Refugee Resettlement” Working Paper 2018:23 Department of Economics School of Economics and Management. Lund University