Predicting industrial property prices with explainable artificial intelligence

Tris Kee and Winky K.O. Ho

Journal of Property Research, 2026, vol. 43, issue 2, 167-187

Abstract: The industrial property market in Hong Kong is a dynamic and complex sector, marked by unique characteristics and atypical market behaviour. This study leverages the predictive power of Gradient Boosting Machines (GBM) to uncover the intricate relationships that drive property prices. Key features such as location, square footage, floor level and proximity to mass transit railway stations are analysed, with Shapley values providing a transparent and interpretable measure of each feature’s impact. Our findings reveal striking non-linear interactions among these features, vividly depicted through beeswarm plots showcasing wide SHAP value distributions that oscillate across the baseline. These insights illuminate the nuanced interplay between property attributes and their market valuation, offering a fresh perspective on the industrial property sector. By equipping stakeholders with actionable intelligence, this research empowers data-driven decision-making, fostering a deeper understanding of the forces shaping property prices in one of the world’s most dynamic real estate markets.

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/09599916.2025.2550976 (text/html)
Access to full text is restricted to subscribers.

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:taf:jpropr:v:43:y:2026:i:2:p:167-187

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/RJPR20

DOI: 10.1080/09599916.2025.2550976

Access Statistics for this article

Journal of Property Research is currently edited by Bryan MacGregor

More articles in Journal of Property Research from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().