Quality of Life Modeling Using Machine Learning Methods

The article is devoted to issues of modeling the quality of life of different countries' population. In the work, the countries of the world were clustered according to the following characteristics: «average age», «human development index», «religion» and «continent», as a result of which they were divided into 5 groups with similar characteristics. This made it possible to model the quality-of-life indicator for each group of countries separately. The models were built using the machine learning method with a preliminary division of the sample into training and test ones. 5 regression models were obtained, each of which corresponded to the conditions of the countries of its cluster. Based on the results of modeling and obtained parameters that affect the quality of life for countries from each cluster, priority areas for improvement were determined in order to improve the population's quality of life. The study proved that the process of modeling such a complex indicator as the quality of life requires significant efforts, as well as constant clarifications in connection with the often-changing circumstances that affect the population's quality of life in different countries