The application of machine learning algorithms for forecasting the quality of life index of the population

Aim. The work aimed to investigate the possibilities of applying various machine learning algorithms to forecast the quality of life index of the population. Objectives. The work seeks to develop predictive models for analyzing the quality of life index of the population of selected countries (Germany, India, the Netherlands, Russia) using various machine learning algorithms based on historical data from the Numbeo website from 2012 to 2025; as well as to systematize and analyze the results of machine learning models for these countries. Methods. The study used machine learning models such as random forest, linear regression, gradient boosting, k-nearest neighbors, and support vector machine. Forecasting the quality of life index of the population is based on data on socio-economic factors for various countries presented in the Numbeo database. Results. A comparative analysis of the results of forecasting the quality of life index of the population of selected countries was performed using machine learning algorithms based on historical data from 2012 to 2025. Particular attention is paid to adjusting the hyperparameters of the models and cross-validation to improve the accuracy of predictions. The analysis demonstrated that the most reliable results can be obtained using an ensemble of machine learning models without taking into account linear regression forecasts. Conclusion. The calculations performed revealed that the gradient boosting model demonstrates the best results. However, in order to improve accuracy and reduce deviations, it is recommended to use an ensemble of models. The use of machine learning in forecasting offers new opportunities for the development of social government programs aimed at improving the quality of life of the population.