Answers are grounded in this paper and cite their sources.
The study demonstrates how mathematical models and machine learning improve real estate cost prediction in Karelia, suggesting better market insights.
Subject. The article substantiates the possibility of using mathematical and computer modeling methods to create new tools enabling to solve the problems of finding the optimal cost of residential real estate in the Northern border region of Russia. Objectives. The study aims at economic and mathematical assessment and forecasting of the cost of residential real estate in the Northern border region of Russia, on the case of the Republic of Karelia. Methods. We created two databases on the cost of residential real estate in the regions of the North-Western Federal District. The first information system contained information on the cost of 1 square meter of apartments in the regions of the Federal District, and the main indicators of demographic and socio-economic development of these subjects for 2000–2024. The second database was created by parsing ads for apartment sales in the Republic of Karelia on the CIAN and Avito websites. Results. The study identified factors with the greatest impact on the formation of the market value of residential real estate in the Northern border region of Russia, and developed new predicative analytical models based on machine learning algorithms to estimate the cost of 1m2 of housing in the Republic of Karelia. Conclusions. The analysis enabled to identify trends, determine the cyclical pricing for the subjects. The developed ARIMA mathematical models can be used at the level of public administration to solve urgent demographic and socio-economic problems, and by legal entities and individuals when purchasing commercial and private real estate.
No takes yet. Share an insight, caveat, or question.
Okrepilov et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: