Real estate decision-making: precision in price prediction through advanced machine learning algorithms

Mohammad A. Shbool, Rand Al-Dmour, Bashar Awad Al-Shboul, Nibal T. Albashabsheh and Najat Almasarwah

International Journal of Housing Markets and Analysis, 2025, vol. 19, issue 3, 771-795

Abstract: PurposeThis study aims to enhance real estate price prediction accuracy using advanced machine learning models, minimizing biases and inconsistencies inherent in traditional appraisal methods. By leveraging support vector regression (SVR) and gradient boosting machine (GBM), this study provides a data-driven approach to property valuation, improving decision-making for buyers, sellers and policymakers. This study also seeks to bridge the gap in machine learning applications for emerging markets like Jordan. This study’s research’s broader goal is to offer a transparent, efficient and reliable tool for property valuation that improves market efficiency and reduces transaction uncertainty.Design/methodology/approachThis study uses machine learning techniques – SVR and GBM – to predict real estate prices in Amman, Jordan. Data was collected from the Department of Lands and Survey, covering residential property sales from March 2023 to December 2023. The data set underwent preprocessing, including one-hot encoding for categorical variables and logarithmic normalization for skewed data. Hyperparameter tuning was performed using grid search, and an ensemble approach compared multiple algorithms. Performance was evaluated using root mean squared error (RMSE), mean absolute percentage error (MAPE) and MAE. The findings were implemented into a user-friendly “PRICE IT” application for real-world application.FindingsThe results demonstrate that SVR outperforms GBM in predicting real estate prices, achieving the lowest RMSE (0.31) and MAPE (25%). The most influential factors in price determination are property area, location and apartment type. The study highlights that machine learning models provide superior accuracy compared to traditional appraisal methods. The findings support the integration of data-driven valuation techniques in real estate markets, reducing reliance on subjective human judgment. A user-friendly application was developed to enable nontechnical users to estimate property prices, making the research practical and impactful.Originality/valueThis study contributes to the growing field of machine learning applications in real estate by demonstrating the effectiveness of SVR and GBM in an emerging market context. Unlike previous research, it focuses on Amman, Jordan, where limited studies have explored advanced machine-learning models for price prediction. The study offers a practical, user-friendly valuation tool that real estate stakeholders can widely adopt. This research enhances decision-making and market efficiency by providing a transparent and objective alternative to traditional appraisal methods.

Keywords: Real estate appraisals; Machine learning; Support vector regression (SVR); Gradient boosting machine (GBM); Property valuation (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.emerald.com/ijhma/article/19/3/771/125 ... g-precision-in-price (text/html)
https://www.emerald.com/ijhma/article-pdf/19/3/771 ... a-01-2025-0004en.pdf (application/pdf)

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:eme:ijhmap:ijhma-01-2025-0004

DOI: 10.1108/IJHMA-01-2025-0004

Access Statistics for this article

International Journal of Housing Markets and Analysis is currently edited by Dr Richard Reed

More articles in International Journal of Housing Markets and Analysis from Emerald Group Publishing Limited
Bibliographic data for series maintained by Emerald Support ().