Informatics. Economics. Management

Development of the K-Means model to identify the most profitable offers on the Moscow real estate market

M. A. Zuev

V. M. Shibaev

K. S. Balanev

DOI: https://doi.org/10.47813/2782-5280-2024-3-2-0212-0218

Keywords: data clustering, K-Means, real estate analysis, selection optimization, machine learning, Moscow real estate market

---

Abstract

The article discusses the application of the K-Means clustering model to analyze the Moscow real estate market. The main focus is on market segmentation in order to identify the most profitable offers. The data used includes parameters of cost, area, proximity to the subway, year of construction and other characteristics of real estate. The elbow method was used to determine the optimal number of clusters, which was subsequently increased to eight for more accurate segmentation. The results showed that cluster 0 represents the most affordable and profitable offers. The K-Means model developed during the study can be used by buyers to optimize the housing selection process, reducing time and financial costs.

---

Author Biographies

M. A. Zuev

Maxim Zuev, student, Department of "BIT", Institute of Engineering and Economics, direction "Applied Informatics", National Research University «Moscow Power Engineering Institute», Moscow, Russia

V. M. Shibaev

Vladimir Shibaev, student, Department of "BIT", Institute of Engineering and Economics, direction "Applied Informatics", National Research University «Moscow Power Engineering Institute», Moscow, Russia

K. S. Balanev

Kirill Balanev, assistant Professor, National Research University «Moscow Power Engineering Institute», Moscow, Russia

---

References

Shi D., Guan J., Zurada J., Levitan A.S. An Innovative Clustering Approach to Market Segmentation for Improved Price Prediction. Journal of International Technology and Information Management. 2015; 24(1): 2. https://doi.org/10.58729/1941-6679.1033

Гужова О.А. Регулирование рынка жилья с помощью кластер-анализа. Научный журнал НИУ ИТМО. Серия «Экономика и экологический менеджмент». 2015; 3: 201-209.

Skovajsa Š. Review of clustering methods used in data-driven housing market segmentation. Real Estate Management and Valuation. 2023; 31(3): 67-74. https://doi.org/10.2478/remav-2023-0022

Крапивина А.А. Факторный и кластерный анализ рынка вторичного жилья. Контентус. 2016; 8(49): 29-35.

Дейтел П., Дейтел Х. Python: искусственный интеллект, большие данные и облачные вычисления. М.: Альпина Паблишер; 2022. 864.

Маккинни Уэс. Python и анализ данных. М.: ДМК Пресс; 2017. 512.

Гитис Л. Х. Статистическая классификация и кластерный анализ. М.: Наука; 2005. 480.

Педрегоса Ф., Варуко Г. Scikit-learn: машинное обучение на Python. Журнал исследований машинного обучения. 2011; 12: 2825-2830.

Баюк И.А., Березин В.В., Иванюк В.И. Практическое применение методов кластеризации, классификации и аппроксимации. М.: Прометей; 2020. 350.

REFERENCES

Shi D., Guan J., Zurada J., Levitan A.S. An Innovative Clustering Approach to Market Segmentation for Improved Price Prediction. Journal of International Technology and Information Management. 2015; 24(1): 2. https://doi.org/10.58729/1941-6679.1033 DOI: https://doi.org/10.58729/1941-6679.1033

Guzhova O.A. Regulirovanie rynka zhil'ya s pomoshch'yu klaster-analiza. Nauchnyj zhurnal NIU ITMO. Seriya «Ekonomika i ekologicheskij menedzhment». 2015; 3: 201-209. (in Russian)

Skovajsa Š. Review of clustering methods used in data-driven housing market segmentation. Real Estate Management and Valuation. 2023; 31(3): 67-74. https://doi.org/10.2478/remav-2023-0022 DOI: https://doi.org/10.2478/remav-2023-0022

Krapivina A.A. Faktornyj i klasternyj analiz rynka vtorichnogo zhil'ya. Kontentus. 2016; 8(49): 29-35. (in Russian)

Dejtel P., Dejtel H. Python: iskusstvennyj intellekt, bol'shie dannye i oblachnye vychisleniya. M.: Al'pina Pablisher; 2022. 864. (in Russian)

Makkinni Ues. Python i analiz dannyh. M.: DMK Press; 2017. 512. (in Russian)

Gitis L. H. Statisticheskaya klassifikaciya i klasternyj analiz. M.: Nauka; 2005. 480. (in Russian)

Pedregosa F., Varuko G. Scikit-learn: mashinnoe obuchenie na Python. Zhurnal issledovanij mashinnogo obucheniya. 2011; 12: 2825-2830. (in Russian)

Bayuk I.A., Berezin V.V., Ivanyuk V.I. Prakticheskoe primenenie metodov klasterizacii, klassifikacii i approksimacii. M.: Prometej; 2020. 350. (in Russian)