Leveraging a novel machine learning approach to forecast income and immigration dynamics

Abstract

Migration is one of the most important topics to emerge in the history of humanity. It is essential to anticipate human migration as exactly as possible in a variety of circumstances, including urban planning, trade, epidemics, the global expansion of diseases, and pandemic preparation, in order to generate successful public policy. Estimating potential future earnings for an individual, a firm, or an entire industry may be accomplished via the use of income projections. These data might be put to use to identify potential areas for growth and investment, as well as to devise strategies for adjusting both the employment landscape and the economy as a whole. It is possible to anticipate immigration by applying machine learning (ML), a technique that is presently used in almost every facet of modern life. In this research work, we presented the ML-based swarm-optimized binary regression-based xgboost method (also known as SO-BRXGB). According to the results of the research, the SO-BRXGB algorithms were the ones that were the most successful in the applications. In conclusion, the machine learning models for human migration prediction that were applied in this study will offer a flexible framework for predicting human migration under a variety of situations.