Housing Price Prediction - Machine Learning and Geostatistical Methods

Cellmer Radosław () and Kobylińska Katarzyna ()
Additional contact information
Cellmer Radosław: Department of Real Estate and Urban Studies, University of Warmia and Mazury in Olsztyn, Prawochenskiego 15, 10-724 Olsztyn, Poland
Kobylińska Katarzyna: Department of Real Estate and Urban Studies, University of Warmia and Mazury in Olsztyn, Prawochenskiego 15, 10-724 Olsztyn, Poland

Real Estate Management and Valuation, 2025, vol. 33, issue 1, 1-10

Abstract: Machine learning algorithms are increasingly often used to predict real estate prices because they generate more accurate results than conventional statistical or geostatistical methods. This study proposes a methodology for incorporating information about the spatial distribution of residuals, estimated by kriging, into selected machine learning algorithms. The analysis was based on apartment prices quoted in the Polish capital of Warsaw. The study demonstrated that machine learning combined with geostatistical methods significantly improves the accuracy of housing price predictions. Local factors that influence housing prices can be directly incorporated into the model with the use of dedicated maps.

Keywords: machine learning; housing prices; geostatistics (search for similar items in EconPapers)
JEL-codes: C45 C53 R20 R32 (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://doi.org/10.2478/remav-2025-0001 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:vrs:remava:v:33:y:2025:i:1:p:1-10:n:1001

DOI: 10.2478/remav-2025-0001

Access Statistics for this article

Real Estate Management and Valuation is currently edited by Sabina Zrobek

More articles in Real Estate Management and Valuation from Sciendo
Bibliographic data for series maintained by Peter Golla ().