Explainable machine learning for urban housing prices: Policy relevant diagnostics across three cities

Cities 2026 Open access

Read full text
Authors: Youngre Noh, Chan Young Park
DOI: 10.1016/j.cities.2026.107266
Cited by: 1
References: 38

Abstract

• Explainable ML is a practical diagnostic complement to hedonic pricing models. • Tree-based models improve out-of-sample R 2 by 0.10–0.35 over linear baselines. • SHAP yields spatially explicit, dollar-valued insights for non-linear thresholds. • Continuous distance gradients reveal income-differentiated proximity premiums. • Diagnostics inform TOD zoning, appraisals, and targeted anti-displacement policies.

Fields of Study & Subjects

Housing Market and Economics Urban Neighborhood and Segregation Studies Spatial and Panel Data Analysis

Publication details

Journal / source
Cities
Publisher
Elsevier BV
Volume
176
Pages
107266–107266
Publication date
27 May 2026
Language
EN