Journal
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
Volume 40, Issue 1, Pages 186-200Publisher
TAYLOR & FRANCIS INC
DOI: 10.1080/07350015.2020.1791133
Keywords
Elastic Net; Google Trends; Machine learning; Random forests; Targeting predictors; U; S; employment growth
Funding
- Danish National Research Foundation [DNRF78]
Ask authors/readers for more resources
This study demonstrates a strong correlation between Google search activity and employment growth in the United States, showing that Google search results are an effective predictor for future employment growth. By constructing a large panel of 172 variables and utilizing Google's own algorithms to find semantically related search queries, the Google Trends model outperforms other predictors in its ability to forecast employment growth.
We show that Google search activity on relevant terms is a strong out-of-sample predictor for future employment growth in the United States over the period 2004-2019 at both short and long horizons. Starting from an initial search term jobs, we construct a large panel of 172 variables using Google's own algorithms to find semantically related search queries. The best Google Trends model achieves an out-of-sampleR(2)between 29% and 62% at horizons spanning from one month to one year ahead, strongly outperforming benchmarks based on a single search query or a large set of macroeconomic, financial, and sentiment predictors. This strong predictability is due to heterogeneity in search terms and extends to industry-level and state-level employment growth using state-level specific search activity. Encompassing tests indicate that when the Google Trends panel is exploited using a nonlinear model, it fully encompasses the macroeconomic forecasts and provides significant information in excess of those.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available