Effective use of machine learning to solve socio-economic problems

Saya Zamanbekovna Sapakova, Arnur Akberdiuly Abdikadirov, Yelidana Yilibule, Dias Manarbekovich Atudinov, Nuray Sabitqyzy Ybyrakhym


To study of the dependence of the offer price of a residential real estate object in Almaty on a number of factors (apartment area; number of rooms; material from which the house is built; floor on which the studied object is located; kitchen area; type of bathroom; presence of a balcony; distance from the city center; availability of an elevator; condition of the apartment in terms of the need for repairs; age of the house; belonging to the primary or secondary real estate market). The obtained machine learning models can be used to make forecasts of the cost of residential real estate, which can be reflected in the development of programs for the socio-economic development of municipalities and the region as a whole, will be in demand by investors, other counterparties in the residential real estate market and individuals. when assessing the acquired social and domestic benefits. The authors see the continuation of research based on the accumulation of an array of information in expanding the possibilities of modeling the cost of apartments, depending not only on the characteristics of apartments, but also on characteristics that reflect the influence of external factors on the regional market of residential real estate.


real estate market, cost of apartments, real estate object, regional real estate market, Almaty, machine learning, algorithms

Full Text:



Elaine M. Worzala, Margarita Lenk, Ana Silva. An Exploration of Neural Networks and Its Application to Real Estate Valuation // Journal of Real Estate Research; American Real Estate Society, vol. 10(2). pp. 185–202, 1995.

Visit Limsombunchai (2004). House Price Prediction: Hedonic Price Model vs. Artificial Neural Network, American Journal of Applied Sciences. 1(3). pp. 193–201.

G. Bernard, J. S. Pathmanathan, R. Lannes, P. Lopez, and E. Bapteste, “Microbial Dark Matter Investigations: How Microbial Studies Transform Biological Knowledge and Empirically Sketch a Logic of Scientific Discovery,” Genome Biol. Evol., vol. 10, no. 3, pp. 707–715, Mar. 2018, doi: 10.1093/gbe/evy031.

GeoPhy : [site]. URL: https://geophy. com/

Yasnitskiy V.L. Neural network modeling in the problem of mass appraisal of residential real estate in the city of Perm // Fundamental research. 2015. No. 10-3. pp. 650–653. URL: http://www.fundamental-research.ru/ru/article/view?id=39274

Surkov F. A., Petkova N. V., Sukhovsky S. F. Neural network methods of data analysis in real estate appraisal "// Izvestia universities. North Caucasian region. Technical sciences. 2016. No. 3. pp. 38-45.

Aref'eva E.A., Kostyaev D.S. Using neural networks to assess the market value of real estate, Bulletin of the Tula State University. Technical science. 2017. Issue. 10, pp. 177–184.

HouseCanary - Residential real estate valuations: [website]. URL: https://www.house canary.com/.

Cho D., Ma S. Dynamic Relationship between Housing Value and Interest Rates in the Korean Housing Market // The Journal of Real Estate Finance and Economics. 2006. Vol. 32, № 2. P. 169–184. DOI: 10.1007/s11146-006-6013-6.

Hwang S.-J., Park M.-S., Lee H.-S., Yoon Y.-S. Analysis of the Korean Real Estate Market and Boosting Policies Focusing on Mortgage Loans: Using System Dynamics // Korean Journal of Construction Engineering and Management. 2010. Vol. 11, № 1. P. 101–112. DOI: 10.6106/kjcem.2010.11.1.101

Mints A.U. Modeling of the pricing process in the housing market by the methods of system dynamics // Technology audit and production reserves. 2016. Т. 5, № 4 (31). pp. 39–45..

Sidorenko O.A. The main directions of economic and mathematical modeling of the real estate market. Statistika i ekonomika [Statistics and Economics], 2013, no. 3, pp. 153–158. (In Russian)

DOI: http://dx.doi.org/10.21533/scjournal.v10i2.215


  • There are currently no refbacks.

Copyright (c) 2021 Saya Zamanbekovna Sapakova

ISSN 2233 -1859

Digital Object Identifier DOI: 10.21533/scjournal

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License