Title: Forecasting real housing price returns of the USA using machine learning: the role of climate risks

Authors: Bruno Tag Sales; Hudson S. Torrent; Rangan Gupta

Addresses: Department of Economics, Universidade Federal do Rio Grande do Sul, Porto Alegre, 90040-000, Brazil ' Department of Statistics, Universidade Federal do Rio Grande do Sul, Porto Alegre, 91509-900, Brazil ' Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa

Abstract: Climate change, a pressing global challenge, has wide-ranging implications for various aspects of our lives, including housing prices. This paper delves into the complex relationship between climate change and real housing price returns in the USA, leveraging a comprehensive dataset and advanced machine learning technique - the stepwise boosting method. This ensemble learning technique significantly enhances our analysis. Our findings suggest that climate change variables can influence real housing price returns, particularly in the short term, but the relationship is complex and varies by region. The adaptive learning capability of step-wise boosting has been crucial in uncovering these insights. This methodological approach not only underscores the importance of employing advanced predictive models in analysing the effects of climate change on urban development but also highlights the potential for informed decision-making, sustainable urban planning, and climate risk mitigation.

Keywords: climate finance; housing market; machine learning; predictive modelling; step-wise boosting; USA.

DOI: 10.1504/IJCEE.2025.147775

International Journal of Computational Economics and Econometrics, 2025 Vol.15 No.3, pp.225 - 246

Received: 01 Aug 2024
Accepted: 26 Nov 2024
Published online: 31 Jul 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article