Searching for a better life: Predicting international migration with online search keywords

• Published in: Journal of development economics Vol. 142; p. 102347
• Main Authors: Böhme, Marcus H., Gröger, André, Stöhr, Tobias
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.01.2020
• Subjects: Google trends; International migration; Migration intention; International migration; O15; J61; Migration intention; Google trends; F22; C82
• ISSN: 0304-3878; 1872-6089
• DOI: 10.1016/j.jdeveco.2019.04.002

Migration data remains scarce, particularly in the context of developing countries. We demonstrate how geo-referenced online search data can be used to measure migration intentions in origin countries and to predict bilateral migration flows. Our approach provides strong additional predictive power for international migration flows when compared to reference models from the migration and trade literature. We provide evidence, based on survey data, that our measures partly reflect genuine migration intentions and that they outperform any of the established predictors of migration flows in terms of predictive power, especially in the bilateral within dimension. Our findings contribute to the literature by (1) providing a novel way for the measurement of migration intentions, (2) allowing real-time predictions of current migration flows ahead of official statistics, and (3) improving the performance of conventional models of migration flows. •Lack of migration data limits research and policy applications.•We use geo-referenced online search data to predict migration flows.•Strong predictive performance compared to benchmark models.•Method can help to measure migration intentions and facilitate policy predictions.