The paper considers the factors influencing the formation of the cost of one square meter of residential real estate in the regions of the Russian Federation, and also develops methods for predicting this indicator using machine learning algorithms. The purpose of the study is to identify the key determinants of price dynamics and build predictive models based on empirical data. The object of the study is the residential real estate market in the region, which includes macroeconomic, demographic and informational characteristics. The subject of the analysis is the influence of a combination of factors on pricing in the housing segment. The methodological base includes machine learning models: Decision Tree, Random Forest and Gradient Boosted Trees. The results indicate a significant impact of factors such as the unemployment rate, average wages, and the intensity of mortgagerelated search queries. The highest accuracy of the forecast was achieved using the regression tree model (R2 = 0.942). The findings emphasize the need to integrate statistical and algorithmic analysis methods in shaping strategies for managing regional real estate markets.
Viktorova et al. (Wed,) studied this question.