Predicting housing price bubbles: the power and limits of selected machine learning methods

Alon Sagi, Avigdor Gal and Dani Broitman

Chapter 18 in Handbook on Big Data, Artificial Intelligence and Cities, 2025, pp 377-389 from Edward Elgar Publishing

Abstract: Can future complex urban phenomena be predicted? This chapter examines whether advanced machine learning (ML) methods can enhance housing price predictability at the level of neighborhoods. The aim of the analysis is to test the ability of ML to detect future housing bubbles and other housing price trends for a future decade at a neighborhood scale. The analysis demonstrates that changes in housing prices can be predicted with a relatively high level of accuracy over a decade ahead. In particular, this is true for situations in which certain neighborhoods develop a process that resembles a housing price bubble. However, the application of ML methods can be costly, both in terms of data preparation and the search for the appropriate algorithm and its adaptation. For housing price predictability, the long short-term memory (LSTM) with data augmentation is a promising technique, while Visual Geometry Group (VGG) 16 is not a good choice, even after several adaptation efforts.

Keywords: Housing price bubbles; Machine learning; Real-estate forecasting; Neighborhood dynamics; Decision trees; Neural networks (search for similar items in EconPapers)
Date: 2025
ISBN: 9781803928043
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.elgaronline.com/doi/10.4337/9781803928050.00026 (application/pdf)
Our link check indicates that this URL is bad, the error code is: 403 Forbidden

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:elg:eechap:21797_18

Ordering information: This item can be ordered from
http://www.e-elgar.com

Access Statistics for this chapter

More chapters in Chapters from Edward Elgar Publishing
Bibliographic data for series maintained by Jack Sweeney ().