Abstract: The tax burden of the regions is influenced by a whole range of factors, among which it is necessary to take into account the natural and climatic conditions. After all, the specialization of the regions, production capabilities, production volumes and, accordingly, the level of tax revenues to the consolidated budget of the Russian Federation depend on them. The article analyzes the tax potential of regions depending on the climatic factor. The subject of this study is a system of statistical indicators characterizing the natural and climatic conditions of the regions (temperature and precipitation in July and January for three years) and the economic results of their activities, including tax revenues to budgets. The aim of the work is to assess the influence of the climatic factor on the tax potential of the regions using the grouping method of cluster analysis.  The research method is cluster analysis (k-means method), implemented using the R programming language and its packages, which allows combining regions according to the similarity in climatic conditions, while minimizing variation within groups and maximizing intergroup differences. The results of the study can be applied in the development of recommendations at the state level on optimizing the tax burden of regions for regions with similar conditions. The novelty of the study lies in the possibility of assessing and comparing the characteristics of regions with similar climatic conditions in terms of tax potential, which is necessary to develop measures for the development of regions and increase their tax potential. As a result of the study, the influence of the climatic factor on the tax potential of the regions and the need to take it into account in combination with other factors is proved.

Abstract: The article analyzes the data of a set of agricultural enterprises and builds machine learning models to predict the tax burden. The subject of this study is a system of statistical indicators of agricultural enterprises that characterize the level of tax burden. The purpose of the study is to predict the tax burden using machine learning methods. The introduction of modern artificial intelligence tools is an integral and inevitable process in all spheres, including in the tax environment. Machine learning methods were used to build models: regression analysis, decision tree, random forest, gradient boosting. Models of forecasting the tax burden depending on a set of factors were built. The high quality of tax burden forecasting models will make it possible to more accurately assess the financial condition of enterprises, calculate profitability, predict profitability and make informed investment management decisions. As a result of forecasting the tax burden, the gradient boosting machine learning model turned out to have the best quality. In general, the model allows you to predict the tax burden better than traditional econometric models and make high-quality forecasts. The introduction of modern forecasting tools based on artificial intelligence methods will allow obtaining highly accurate forecasts with minimal time, which will increase the efficiency of enterprises and the level of production.