2020/07/27 by Jeremy Ferwerda, Ferwerda, Jeremy, Nicholas Adams-Cohen +11 · 2 citations
Social Sciences · #Applications (stat.AP) #Computers and Society (cs.CY) #FOS: Computer and information sciences #FOS: Economics and business #General Economics (econ.GN) #Machine Learning (cs.LG) #Migration and Labor Dynamics #Urban Transport and Accessibility #Urban, Neighborhood, and Segregation Studies
paper · pdf · doi:10.48550/arxiv.2007.13902
openalex publication_date 2020/07/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
A growing number of countries have established programs to attract immigrants\nwho can contribute to their economy. Research suggests that an immigrant's\ninitial arrival location plays a key role in shaping their economic success.\nYet immigrants currently lack access to personalized information that would\nhelp them identify optimal destinations. Instead, they often rely on\navailability heuristics, which can lead to the selection of sub-optimal landing\nlocations, lower earnings, elevated outmigration rates, and concentration in\nthe most well-known locations. To address this issue and counteract the effects\nof cognitive biases and limited information, we propose a data-driven decision\nhelper that draws on behavioral insights, administrative data, and machine\nlearning methods to inform immigrants' location decisions. The decision helper\nprovides personalized location recommendations that reflect immigrants'\npreferences as well as data-driven predictions of the locations where they\nmaximize their expected earnings given their profile. We illustrate the\npotential impact of our approach using backtests conducted with administrative\ndata that links landing data of recent economic immigrants from Canada's\nExpress Entry system with their earnings retrieved from tax records.\nSimulations across various scenarios suggest that providing location\nrecommendations to incoming economic immigrants can increase their initial\nearnings and lead to a mild shift away from the most populous landing\ndestinations. Our approach can be implemented within existing institutional\nstructures at minimal cost, and offers governments an opportunity to harness\ntheir administrative data to improve outcomes for economic immigrants.\n