Machine Learning Methods in Individual Migration Behavior

Abstract

Machine learning is described as “a field of computer science that gives a machine the ability to learn”. In fact, machine learning is considered as a sub branch of Artificial Intelligence(AI). In recent years the rise of big data and cloud computing gives AI expert and specifically machine learning expert to dive deeply in data and extract knowledge from it by using machine learning algorithms. In this paper we try to introduce the basic concepts of machine learning algorithms including supervised learning, unsupervised learning and reinforcement learning and its usage in different applications. We describe specifically how to use machine learning in migration process modeling and focus on an approach for migration description, that is based on one of machine learning methods, the decision tree algorithm. We apply this method for the description of the economic behavior of an individual in the question of continuing his work in Russia based on the panel data and the data from the sociological survey. The accuracy of our estimation using decision tree is 67 percent for this specific task. All in all, the main objective of this paper is to introduce the important aspects of machine learning and its usages in the state-of-the-art technologies.