Performance Evaluation of Machine Learning Algorithms and the Hedonic Model in Property Valuation: Emphasizing Structural and Spatial Attributes

saebi, majid; karimi, mohammad

[Home ] [Archive]

[ فارسی ]

Journal of Geomatics Science and Technology

Main Menu

Home

Browse

Journal Info

Guide for Authors

Submit Manuscript

Articles archive

For Reviewers

Contact us

Site Facilities

Reviewers

Search in website

Receive site information

Volume 15, Issue 4 (6-2026)

JGST 2026, 15(4): 45-61

Back to browse issues page

Performance Evaluation of Machine Learning Algorithms and the Hedonic Model in Property Valuation: Emphasizing Structural and Spatial Attributes

Majid Saebi ^*

, Mohammad Karimi

Abstract: (133 Views)

Accurate valuation of residential properties is crucial for decision-making among stakeholders, housing market experts, and urban managers. Given the multifaceted and complex nature of factors influencing property values, integrating machine learning techniques with spatial analysis can significantly enhance prediction accuracy. In this research, a hybrid dataset comprising structural characteristics and spatial attributes extracted within a GIS environment was utilized. Employing four machine learning algorithms Random Forest, Gradient Boosting Regressor, XGBoost, and CatBoost the process of feature vector extraction and optimization was conducted for property valuation. The proposed framework is designed around two valuation approaches: the first models the total property value (final price of the residential unit), while the second estimates the price per square meter. By normalizing for area, the second approach facilitates better comparability among properties. In both scenarios, the performance of the machine learning models was compared against the classical Hedonic model based on Ordinary Least Squares (OLS) regression. The results of the study, conducted in District 5 of Tehran over a two-month period, indicate that machine learning models delivered superior performance compared to the Hedonic model in both approaches. Specifically, the CatBoost algorithm demonstrated the highest efficiency, achieving a Root Mean Square Error (RMSE) of 0.30, an R-squared (R²) of 0.82, and a Mean Absolute Percentage Error (MAPE) of 10.04%; whereas the Hedonic model achieved, at best, an RMSE of 0.36 and a MAPE of 12.13%. These findings underscore the significant impact of integrating spatial analysis with machine learning techniques particularly the CatBoost algorithm in the valuation of residential properties.

Keywords: Residential Property Valuation, Geospatial Information System, Machine Learning, Hedonic Model, Spatial Attributes

Full-Text [PDF 1447 kb] (14 Downloads)

Type of Study: Research | Subject: GIS
Received: 2026/01/8 | Accepted: 2026/06/26

References

1. Y. Yu, J. Lu, D. Shen, and B. Chen, "Research on real estate pricing methods based on data mining and machine learning," Neural Comput & Applic, vol. 33, no. 9, pp. 3925-3937, May 2021, doi: 10.1007/s00521-020-05469-3. [DOI:10.1007/s00521-020-05469-3]

2. W. K. O. Ho, B.-S. Tang, and S. W. Wong, "Predicting property prices with machine learning algorithms," Journal of Property Research, vol. 38, no. 1, pp. 48-70, Jan. 2021, doi: 10.1080/09599916.2020.1832558. [DOI:10.1080/09599916.2020.1832558]

3. Y. Kang et al., "Understanding house price appreciation using multi-source big geo-data and machine learning," Land Use Policy, vol. 111, p. 104919, 2021. [DOI:10.1016/j.landusepol.2020.104919]

4. R. Cellmer and R. Trojanek, "Towards increasing residential market transparency: Mapping local housing prices and dynamics," ISPRS International Journal of Geo-Information, vol. 9, no. 1, p. 2, 2019. [DOI:10.3390/ijgi9010002]

5. S. Smirnov and V. Tlostanov, "Moscow Real Estate: Pricing Analysis Through the Prism of Statistics and Machine Learning," Available at SSRN 3374436, 2019, Accessed: Oct. 29, 2023. [Online]. Available: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3374436 [DOI:10.2139/ssrn.3374436]

6. P. Ai, "Residential land value modelling," Faculty of Geo-Information Science and Earth Observationof the University of Twente. 2005.[An electronic resource]. Access mode: https://www. itc. nl/library/papers_2005/msc/upla/ai_ping. pdf (дата обращения: 29.12. 2017), free. Heading from the screen, 2005, Accessed: Jun. 17, 2024. [Online]. Available: https://www.muthar-alomar.com/wp-content/uploads/2013/01/Residential-Land-Value.pdf

7. T. F. Sing, J. J. Yang, and S. M. Yu, "Boosted Tree Ensembles for Artificial Intelligence Based Automated Valuation Models (AI-AVM)," J Real Estate Finan Econ, vol. 65, no. 4, pp. 649-674, Nov. 2022, doi: 10.1007/s11146-021-09861-1. [DOI:10.1007/s11146-021-09861-1]

8. H. T. Sergoyan and G. V. Bezirganyan, "Automated Real Estate Valuation With Machine Learning: A Case Study on Apartment Sales in Yerevan," Journal of Architectural and Engineering Research, vol. 2, pp. 83-91, 2022. [DOI:10.54338/27382656-2022.2-012]

9. A. Guerra, A. Garces, and L. Chacon, "Apartment Pricing Prediction in the Panamanian Real Estate Market: A Machine Learning Perspective," Available at SSRN 4493347, 2023, Accessed: Jun. 02, 2024. [Online]. Available: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4493347 [DOI:10.2139/ssrn.4493347]

10. C. Yiorkas and T. Dimopoulos, "Implementing GIS in real estate price prediction and mass valuation: the case study of Nicosia District," in Fifth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2017), SPIE, 2017, pp. 112-128. Accessed: Oct. 29, 2023. [Online]. Available: https://www.spiedigitallibrary.org/conference-proceedings-of-spie/10444/104440F/Implementing-GIS-in-real-estate-price-prediction-and-mass-valuation/10.1117/12.2280255.short [DOI:10.1117/12.2280255]

11. R. Cellmer, A. Cichulska, and M. Belej, "Spatial analysis of housing prices and market activity with the geographically weighted regression," ISPRS International Journal of Geo-Information, vol. 9, no. 6, p. 380, 2020. [DOI:10.3390/ijgi9060380]

12. Y. Xiao, "BIG DATA FOR COMPREHENSIVE ANALYSIS OF REAL ESTATE MARKET," 2022, Accessed: Jun. 17, 2024. [Online]. Available: https://scholarworks.lib.csusb.edu/etd/1596/

13. L. H. Choy and W. K. Ho, "The Use of Machine Learning in Real Estate Research," Land, vol. 12, no. 4, p. 740, 2023. [DOI:10.3390/land12040740]

14. T. D. Phan, "Housing price prediction using machine learning algorithms: The case of Melbourne city, Australia," in 2018 International conference on machine learning and data engineering (iCMLDE), IEEE, 2018, pp. 35-42. Accessed: Oct. 29, 2023. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/8614000/ [DOI:10.1109/iCMLDE.2018.00017]

15. F. Lorenz, J. Willwersch, M. Cajias, and F. Fuerst, "Interpretable machine learning for real estate market analysis," Real Estate Economics, vol. 51, no. 5, pp. 1178-1208, Sep. 2023, doi: 10.1111/1540-6229.12397. [DOI:10.1111/1540-6229.12397]

16. A. Jafari and M. R. Delavar, "Estimating the price of residential properties based on the optimal support vector machine," in International Conference of GIScience: Bassis and Trans/Interdisiciplanary Applications, Mashhad, Iran, 2021. Accessed: Nov. 09, 2024. [Online]. Available: https://www.researchgate.net/profile/Ali-Jafari-47/publication/361433368_Estimating_the_price_of_residential_properties_based_on_the_optimal_support_vector_machine/links/62b14230dc817901fc6ef931/Estimating-the-price-of-residential-properties-based-on-the-optimal-support-vector-machine.pdf

17. K. Koutroumbas and S. Theodoridis, Pattern Recognition. Academic Press, 2008.

18. M. V. A. William, S. Ramesh, R. Cep, S. K. Mahalingam, and M. Elangovan, "DPGWO Based Feature Selection Machine Learning Model for Prediction of Crack Dimensions in Steam Generator Tubes," Applied Sciences, vol. 13, no. 14, p. 8206, 2023. [DOI:10.3390/app13148206]

19. J. T. Hancock and T. M. Khoshgoftaar, "CatBoost for big data: an interdisciplinary review," J Big Data, vol. 7, no. 1, p. 94, Dec. 2020, doi: 10.1186/s40537-020-00369-8. [DOI:10.1186/s40537-020-00369-8]

20. X. Ding, W. Wang, Y. Zhang, and X. Zhong, "Machine Learning-based Models for House Price Prediction in Provincial Administrative Regions of China," in 2022 7th International Conference on Financial Innovation and Economic Development (ICFIED 2022), Atlantis Press, 2022, pp. 221-229. Accessed: Jun. 04, 2024. [Online]. Available: https://www.atlantis-press.com/proceedings/icfied-22/125971699

21. S. Levantesi and G. Piscopo, "The importance of economic variables on London real estate market: A random forest approach," Risks, vol. 8, no. 4, p. 112, 2020. [DOI:10.3390/risks8040112]

22. J. Cai, K. Xu, Y. Zhu, F. Hu, and L. Li, "Prediction and analysis of net ecosystem carbon exchange based on gradient boosting regression and random forest," Applied energy, vol. 262, p. 114566, 2020. [DOI:10.1016/j.apenergy.2020.114566]

23. J. H. Friedman, "Greedy function approximation: a gradient boosting machine," Annals of statistics, pp. 1189-1232, 2001. [DOI:10.1214/aos/1013203451]

24. K. Baur, M. Rosenfelder, and B. Lutz, "Automated real estate valuation with machine learning models using property descriptions," Expert Systems with Applications, vol. 213, p. 119147, 2023. [DOI:10.1016/j.eswa.2022.119147]

25. Q. Gao, V. Shi, C. Pettit, and H. Han, "Property valuation using machine learning algorithms on statistical areas in Greater Sydney, Australia," Land Use Policy, vol. 123, p. 106409, 2022. [DOI:10.1016/j.landusepol.2022.106409]

26. J. Avanijaa, "Prediction of house price using xgboost regression algorithm," Turkish Journal of Computer and Mathematics Education (TURCOMAT), vol. 12, no. 2, pp. 2151-2155, 2021. [DOI:10.17762/turcomat.v12i2.1870]

27. T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System," in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco California USA: ACM, Aug. 2016, pp. 785-794. doi: 10.1145/2939672.2939785. [DOI:10.1145/2939672.2939785]

28. S. Rezaeian, H. Asgari, and B. Darvishi, "The study of determinants of rent housing in Ilam City based on hedonic spatial econometrics," Journal of urban economics and management, vol. 7, no. 26, pp. 17-30, 2019.

29. H. Amirnejad, "The impact of Rasht Eynak Lagoon on housing price of the region by using hedonic pricing method," in The impact of Rasht Eynak Lagoon on housing price of the region by using hedonic pricing method: Amirnejad, Hamid, 2016. Accessed: Jun. 18, 2024. [Online]. Available: https://www.zbw.eu/econis-archiv/bitstream/11159/602/1/iueam-v4n16p37-en.pdf

30. M. A Milani and M. Haddadi, "Metro and Its Effect on Residential Property Prices (Tehran)," Journal of Economic Research (Tahghighat-E-Eghtesadi), vol. 47, no. 4, pp. 79-96, 2013.

31. سازمان فناوری اطلاعات و ارتباطات شهرداری تهران, امارنامه شهرداری تهران (سالنامه شهر تهران سال 1399). 1399.

Send email to the article author

Add your comments about this article

Mendeley

Zotero

RefWorks

saebi M, karimi M. Performance Evaluation of Machine Learning Algorithms and the Hedonic Model in Property Valuation: Emphasizing Structural and Spatial Attributes. JGST 2026; 15 (4) :45-61
URL: http://jgst.issgeac.ir/article-1-1249-en.html

Rights and permissions
	This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Volume 15, Issue 4 (6-2026)

Back to browse issues page