Modeling and forecasting net migration levels in Africa: using machine learning methodologies

Abstract

This study employs machine learning models, including ARIMA and Prophet, to forecast net migration, using Djibouti's 1950-2023 data as a case study. Predictions extend to 2100, comparing results with UN projections. The research highlights the potential of advanced modeling techniques to improve migration forecasting, offering scalable tools for policymakers to address global mobility challenges.