AI-based matching improves refugee employment in a double-blind randomized trial
Abstract
Refugee integration is a central policy challenge for host countries, and where governments initially place refugees shapes their integration trajectories. Yet placement officers often have limited information about where each case is most likely to succeed. Algorithmic refugee matching uses administrative data, machine learning, and constrained optimization to recommend employment-optimized placements in real time as cases arrive, with human placement officers retaining final authority. Between January 2020 and June 2023, the Swiss State Secretariat for Migration randomly assigned about 2,000 refugee cases to receive a canton recommendation either algorithmically optimized for employment or drawn to approximate existing procedures, with placement officers and refugees blinded to assignment. The two arms used identical but separate canton and origin-group quotas, so gains reflect better refugee-canton matching rather than reallocation toward stronger labor markets. The trial began just before the COVID-19 pandemic shifted labor-market conditions. For the pre-registered primary outcome -- the share of months employed during the first three years -- the pooled intention-to-treat (ITT) estimate across the 2020-2023 placement cohorts was +2.2 percentage points (about 10% of the 22.3% control mean; 95% CI [+0.05, +4.33]), rising to +3.9 pp (about 17%; [+1.11, +6.68]) for the post-COVID 2022-2023 cohorts. Effects grew over time: at 36 months, the pooled ITT on the employment rate was +5.2 pp (about 11%; 95% CI [+1.10, +9.25]) -- comparable to the gains from hundreds of hours of intensive language training. Overall, the results provide rare field evidence that AI-based decision support can improve high-stakes public-sector allocation, offering a scalable, low-cost way to raise refugee employment.
Related
- Where to weight? Estimating population causal effects with weighted double score matching in complex surveys
- Matching Randomized First-Order Bounds for Higher-Order Smooth Nonconvex Optimization
- Matching Lower Bounds for Randomized First-Order Methods in Hessian-Lipschitz Nonconvex Optimization
- Matching Randomized Bounds for Finite-Sum Nonconvex-Concave Optimization
- Second-order consistency for learning chaotic dynamics via randomized Jacobian matching
BibTeX
@misc{bansak2026aibased,
title = {{AI-based matching improves refugee employment in a double-blind randomized trial}},
author = {Kirk Bansak and Jens Hainmueller and Dominik Hangartner and Jeremy Ferwerda and Elisabeth Paulson and Angie Delevoye and Nicholas Adams-Cohen and Ashwin Ramaswami and Selina Kurer and Joelle Pianzola and Michael Hotard},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.35448},
eprint = {2609.35448},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.35448},
}
RIS
TY - UNPB
TI - AI-based matching improves refugee employment in a double-blind randomized trial
AU - Kirk Bansak
AU - Jens Hainmueller
AU - Dominik Hangartner
AU - Jeremy Ferwerda
AU - Elisabeth Paulson
AU - Angie Delevoye
AU - Nicholas Adams-Cohen
AU - Ashwin Ramaswami
AU - Selina Kurer
AU - Joelle Pianzola
AU - Michael Hotard
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.35448
UR - https://arxiv.org/abs/2609.35448
AB - Refugee integration is a central policy challenge for host countries, and where governments initially place refugees shapes their integration trajectories. Yet placement officers often have limited information about where each case is most likely to succeed. Algorithmic refugee matching uses administrative data, machine learning, and constrained optimization to recommend employment-optimized placements in real time as cases arrive, with human placement officers retaining final authority. Between January 2020 and June 2023, the Swiss State Secretariat for Migration randomly assigned about 2,000 refugee cases to receive a canton recommendation either algorithmically optimized for employment or drawn to approximate existing procedures, with placement officers and refugees blinded to assignment. The two arms used identical but separate canton and origin-group quotas, so gains reflect better refugee-canton matching rather than reallocation toward stronger labor markets. The trial began just before the COVID-19 pandemic shifted labor-market conditions. For the pre-registered primary outcome -- the share of months employed during the first three years -- the pooled intention-to-treat (ITT) estimate across the 2020-2023 placement cohorts was +2.2 percentage points (about 10% of the 22.3% control mean; 95% CI [+0.05, +4.33]), rising to +3.9 pp (about 17%; [+1.11, +6.68]) for the post-COVID 2022-2023 cohorts. Effects grew over time: at 36 months, the pooled ITT on the employment rate was +5.2 pp (about 11%; 95% CI [+1.10, +9.25]) -- comparable to the gains from hundreds of hours of intensive language training. Overall, the results provide rare field evidence that AI-based decision support can improve high-stakes public-sector allocation, offering a scalable, low-cost way to raise refugee employment.
ER -