Document Type


Publication Date





The U.S. housing market, after the Global Financial Crisis (GFC), has been extensively studied from several dimensions to assess the causes for the price crash. In this paper, we study and compare five themes related to house price behavior and identify common determinants that drive prices. The themes studied include the macroeconomic business cycle environment, monetary policy, the global saving glut, the fundamentals of the housing market, and lastly housing expectations which may be associated with bubbles. We employ a neural network methodology to capture and explore the relative importance of non-linear relationships not found in classical regression modeling using monthly data between key market features and house prices. Additionally, given bubble identification may be model dependent, we use the structure of model forecast errors (residuals) to identify the potential presence of bubbles. The potential presence of a bubble can be measured against the features within a model theme. CUSUM tests show potential structural breaks (bubbles) in two of our themes around the time of the GFC.


Author Posting. © Anastasios Malliaris, 2023. This is the author's version of the work. It is posted here by permission of Anastasios Malliaris for personal use, not for redistribution.

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.