Search and Predictability of Prices in the Housing Market

Abstract

We develop a new housing search index (HSI) extracted from online search activity on a limited
set of keywords related to the house buying process. We show that the HSI has strong predictive
power over subsequent changes in house prices, both in-sample and out-of-sample and after
controlling for the effect of commonly used predictors, and relate our findings to models of
search-induced frictions. Our results imply that search data can be used as an early indicator
of where the market is going.

Keywords: Internet search, housing markets, housing demand, forecasting, frictions, inelastic housing supply.

JEL Classification: C10, E17, G10, R3