Credit: Unsplash/CC0 public domain
A new home price forecasting model based on consumer demand predicts home prices will fall 5% nationwide and 12% in San Diego County by the end of this year. The pattern, which highlights online search activity, was recently published in a new study from the University of California San Diego’s Rady School of Management.
The model’s predictions have been shown to be up to 70% accurate and are unique to other price predictors, such as Zillow, Goldman Sachs and Redfin, because they consider a variety of factors such as interest rates, wage growth, unemployment and housing supply. Whereas the Housing Search Index created by Allan Timmermann of the Rady School and collaborators at the University of Arhus in Denmark, focuses on consumer demand by tracking how quickly potential buyers use the internet to search for homes.
“It’s one of the purest measures of potential demand you can get because the first thing you do when you’re looking for a home or are interested in buying a home is go on the Internet and see what’s available,” said Timmermann, a distinguished finance professor at Rady School. “A home searcher leaves a big footprint with their online search activity due to the time it takes, often several months, to find something that is the right fit.”
Cities like San Diego have home prices falling more than the national average because that’s where the market has warmed the most during the pandemic, Timmermann said.
“What you saw after the lockdowns in March 2020 was that the sun and the suburbs became a big thing,” Timmermann said. “People were transitioning to working from home, so they wouldn’t have to be near their workplace and therefore could cut their area altogether, choosing to live somewhere with more space and a better climate. San Diego has a lot of suburbs and the desirable weather, of course.”
These tracts and limited supply have caused prices to skyrocket across the county, but the market has cooled 2.5% since May of 2022, when prices peaked.
“Many households have been locked out of the market, so we are now seeing levels adjust,” Timmermann said.
But house prices in other cities are expected to fall even more. Phoenix, AZ is expected to have the largest decline at 18%. Other metropolitan areas where prices are expected to decline include Stockton-Lodi, CA (down 13%), Las Vegas, NV (down 13%), followed by San Diego and Tucson, AZ. Cities with the greatest price stability include the Scranton-Wilkes-Barre-Hazleton, PA and Kansas City, MO metropolitan area, both projected to be up 2%. Other cities with stable price forecasts include Hartford, CT, Harrisburg, PA and Omaha, NE.
Timmermann added that the predictive power of Internet searches tends to be a reliable indicator of where the market is going in the short to medium term, as fluctuations in demand matter more than changes in supply, which tends to be fairly stable over future horizons. Shorter.
One of the main differences between the UC San Diego model for forecasting house prices and other commercial price predictors is that the data behind the housing search index is not landlords. The methodology is fully transparent and replicable as the study, published in Management sciencesit’s public, so anyone can see how it works.
The formula begins with tracking keywords like “buying a home” and related search terms in Google Trends, a free website that analyzes the popularity of top search queries in Google Search. This data is compared with data on home tours and written offers, which allows researchers to predict prices in the short and long term.
“The cost of your time and the intensity with which you search and the number of people searching really reflect the underlying interest in buying a home,” Timmermann said. “At the end of the day, the higher the demand, the higher home prices typically will be.”
Co-authors of the management science paper include Stig Møller, Thomas Pedersen and Christian Schütte of the University of Arhus.
Stig Vinther Møller et al, Price research and predictability in the real estate market, Management sciences (2023). DOI: 10.1287/mnsc.2023.4672
Provided by the University of California – San Diego
Citation: New UC San Diego model predicts home prices to fall up to 18% this year (2023, Feb. 16) Retrieved Feb. 16, 2023 from
This document is subject to copyright. Except in all propriety for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.