发表机构
University of California, Berkeley; Stanford University; ETH Zurich; Dartmouth College; Harvard Business School（加州大学伯克利分校; 斯坦福大学; 苏黎世联邦理工学院; 达特茅斯学院; 哈佛商学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过瑞士双盲随机试验证明，基于AI的算法匹配可显著提高难民就业率，三年内提升约5.2个百分点，提供低成本可扩展的公共部门决策支持证据。
AI 中文摘要
难民融入是接收国面临的核心政策挑战，政府最初安置难民的地点会塑造其融入轨迹。然而，安置官员往往缺乏关于每个案件最可能成功安置地点的有限信息。算法难民匹配利用行政数据、机器学习和约束优化，在案件到达时实时推荐就业优化的安置地点，而人类安置官员保留最终决定权。在2020年1月至2023年6月期间，瑞士联邦移民事务秘书处随机分配了约2000个难民案件，以接受要么针对就业进行算法优化的州推荐，要么近似于现有程序的推荐，安置官员和难民均对分配不知情。两个组使用了相同但独立的州和原籍国配额，因此收益反映了更好的难民-州匹配，而非向更强劲劳动力市场的重新分配。试验恰在COVID-19大流行改变劳动力市场状况之前开始。对于预先注册的主要结果——前三年内就业月份的比例——2020-2023年安置队列的合并意向治疗（ITT）估计为+2.2个百分点（约为22.3%对照组均值的10%；95%置信区间[+0.05, +4.33]），在COVID后的2022-2023年队列中上升至+3.9个百分点（约17%；[+1.11, +6.68]）。效应随时间增长：在36个月时，就业率的合并ITT为+5.2个百分点（约11%；95%置信区间[+1.10, +9.25]）——与数百小时强化语言培训的收益相当。总体而言，结果提供了罕见的现场证据，表明基于AI的决策支持可以改善高风险的公共部门分配，提供了一种可扩展、低成本的方式来提高难民就业。
英文摘要
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.
Comments36 pages main text, 22 pages Supplementary Information (appended)
