Abstract
To make effective decisions, consumers, executives and policymakers must make predictions. However, most data sources, whether from the government or businesses, are available only after a substantial lag, at a high level of aggregation, and for a small set of variables that were defined in advance. This hampers real-time prediction. A critical advance in IT research has been the development of powerful search engines and the underlying Internet infrastructure. We demonstrate a highly accurate but simple way to predict future business activities by using data from such search engines. Applying our methodology to predict housing trends, we find that our index of housing search terms can predict future quantities and prices in the housing market. During our sample period, each percentage rise in our housing search index predicts sales of 121,400 additional houses in the next quarter. This approach can be applied to other markets, transforming the future of prediction.
Recommended Citation
Wu, Lynn and Brynjolfsson, Erik, "The Future of Prediction: How Google Searches Foreshadow Housing Prices and Quantities" (2009). ICIS 2009 Proceedings. 147.
https://aisel.aisnet.org/icis2009/147