Due to international migration’s growing importance in modern countries’ lives, there is an increasing need for reliable and relevant forecasts of this process, especially in today’s turbulent world. However, established migration forecasting procedures suffer from a number of limitations, against which innovative approaches based on big data, notably online searches made by potential migrants, offer many advantages. Because of their novelty, such tools have not yet revealed their full explanatory and predictive properties. The work explores the possibility of using these tools to predict the population flows within the post-Soviet space. We hypothesize that there is a there is a statistical relationship between online queries about migration to Russia made by residents of Kyrgyzstan, Tajikistan and Uzbekistan and subsequent human flows from these countries to Russia. The hypothesis was tested using the migration statistics of Rosstat, the Federal State Statistics Service of the Russian Federation, Google Trends data on search intensity, and Yandex Wordstat service of word matching for validation of search images. As a result of correlation and regression, we found a moderate dependence of the dynamics of human flows on previous queries, which is most evident at a lag of 6–9 months and at zero lag. Obtaining more accurate results in this and similar studies is hindered by the initial limited predictability of migration behavior due to its contextual, sometimes situational and irrational nature, as well as “noisiness” of statistics of queries and often the flows themselves. The search for universal algorithms of determination of relations between queries and migration flows is seen as the main direction of research in this field.

The article was prepared within the project “Post-crisis world order: Challenges and technologies, competition and cooperation” supported by the grant from Ministry of Science and Higher Education of the Russian Federation program for research projects in priority areas of scientific and technological development (Agreement no. 075-15-2020-783).