Software implementation of ensemble models for the analysis of regional socio-economic development indicators

To predict indicators, modern approaches based on machine learning are increasingly being used, as a result, additional tools appear for quantitatively assessing the level of development of socio-economic systems. One of the relevant approaches in machine learning is the use of ensemble methods. The purpose of this study is to develop an approach for processing panel data using special regression models, in particular, the ensembles. An application is presented to implement and compare various regression models, including GPBoost, for panel data used in regional statistics. The application was tested on the example of assessing the innovative potential of Russian regions.