Jeremy Ferwerda

Improving refugee integration through data-driven algorithmic assignment

Data-driven refugee assignment The continuing refugee crisis has made it necessary for governments to find ways to resettle individuals and families in host communities. Bansak et al. used a machine learning approach to develop an algorithm for geographically placing refugees to optimize their overall employment rate. The authors developed and tested the algorithm on segments of registry data from the United States and Switzerland. The algorithm improved the employment prospects of refugees in the United States by ∼40% and in Switzerland by ∼75%. Science, this issue p. 325 A machine learning–based algorithm for assigning refugees can improve their employment prospects over current approaches. Developed democracies are settling an increased number of refugees, many of whom face challenges integrating into host societies. We developed a flexible data-driven algorithm that assigns refugees across resettlement locations to improve integration outcomes. The algorithm uses a combination of supervised machine learning and optimal matching to discover and leverage synergies between refugee characteristics and resettlement sites. The algorithm was tested on historical registry data from two countries with different assignment regimes and refugee populations, the United States and Switzerland. Our approach led to gains of roughly 40 to 70%, on average, in refugees’ employment outcomes relative to current assignment practices. This approach can provide governments with a practical and cost-efficient policy tool that can be immediately implemented within existing institutional structures.

KRLS: A Stata Package for Kernel-Based Regularized Least Squares

The Stata package krls implements kernel-based regularized least squares (KRLS), a machine learning method described in Hainmueller and Hazlett (2014) that allows users to tackle regression and classi cation problems without strong functional form assumptions or a speci cation search. The flexible KRLS estimator learns the functional form from the data, thereby protecting inferences against misspeci cation bias. Yet it nevertheless allows for interpretability and inference in ways similar to ordinary regression models. In particular, KRLS provides closed-form estimates for the predicted values, variances, and the pointwise partial derivatives that characterize the marginal e ects of each independent variable at each data point in the covariate space. The method is thus a convenient and powerful alternative to OLS and other GLMs for regression-based analyses. We also provide a companion package and replication code that implements the method in R.

Explaining opposition to refugee resettlement: The role of NIMBYism and perceived threats

Support for refugee resettlement declines when citizens consider resettlement within their communities or face threatening frames. One week after President Donald Trump signed a controversial executive order to reduce the influx of refugees to the United States, we conducted a survey experiment to understand American citizens’ attitudes toward refugee resettlement. Specifically, we evaluated whether citizens consider the geographic context of the resettlement program (that is, local versus national) and the degree to which they are swayed by media frames that increasingly associate refugees with terrorist threats. Our findings highlight a collective action problem: Participants are consistently less supportive of resettlement within their own communities than resettlement elsewhere in the country. This pattern holds across all measured demographic, political, and geographic subsamples within our data. Furthermore, our results demonstrate that threatening media frames significantly reduce support for both national and local resettlement. Conversely, media frames rebutting the threat posed by refugees have no significant effect. Finally, the results indicate that participants in refugee-dense counties are less responsive to threatening frames, suggesting that proximity to previously settled refugees may reduce the impact of perceived security threats.

Determinants of refugee naturalization in the United States

Significance Despite the scale of the US refugee resettlement program, policymakers and the public lack systematic information on how refugees adapt to their new environment. We focus on naturalization as a key measure of integration and draw on administrative data to provide direct estimates of the naturalization rates among refugees. Our results show that, on average, refugees acquire citizenship faster than other lawful permanent residents. We also identify the set of factors that promote or constrain naturalization among refugees. These findings have implications for policymakers seeking to improve the integration of refugees within the United States. The United States operates the world’s largest refugee resettlement program. However, there is almost no systematic evidence on whether refugees successfully integrate into American society over the long run. We address this gap by drawing on linked administrative data to directly measure a long-term integration outcome: naturalization rates. Assessing the full population of refugees resettled between 2000 and 2010, we find that refugees naturalize at high rates: 66% achieved citizenship by 2015. This rate is substantially higher than among other immigrants who became eligible for citizenship during the same period. We also find significant heterogeneity in naturalization rates. Consistent with the literature on immigration more generally, sociodemographic characteristics condition the likelihood of naturalization. Women, refugees with longer residency, and those with higher education levels are more likely to obtain citizenship. National origins also matter. While refugees from Iran, Iraq, and Somalia naturalize at higher rates, those from Burma, Ukraine, Vietnam, and Liberia naturalize at lower rates. We also find naturalization success is significantly shaped by the initial resettlement location. Placing refugees in areas that are urban, have lower rates of unemployment, and have a larger share of conationals increases the likelihood of acquiring citizenship. These findings suggest pathways to promote refugee integration by targeting interventions and by optimizing the geographic placement of refugees.