In Search of a Job: Forecasting Employment Growth in the US using Google Trends

We show that Google search activity on relevant terms is a strong out-of-sample predictor of future employment growth in the US and that it greatly outperforms benchmark predictive models based on macroeconomic, financial, and sentiment variables. Using a subset of ten keywords, we construct a panel with 211 variables using Google’s own algorithms to find related search queries. We use Elastic Net variable selection in combination with Partial Least Squares to extract the most important information from a large set of search terms. Our forecasting model, which can be constructed in real time and is free from revisions, delivers an out-of-sample R^2 statistic of 65% to 88% for horizons between one month and one year ahead over the period 2008-2017, which compares to between roughly 30% and 60% for the benchmark models.

[1]  Seth Pruitt,et al.  Market Expectations in the Cross Section of Present Values , 2012 .

[2]  David E. Rapach,et al.  Forecasting US state-level employment growth: An amalgamation approach , 2012 .

[3]  J. Stock,et al.  Macroeconomic Forecasting Using Diffusion Indexes , 2002 .

[4]  Hossein Asgharian,et al.  Economic Policy Uncertainty and Long-Run Stock Market Volatility and Correlation , 2018 .

[5]  Nonstationary Cointegration in the Fractionally Cointegrated VAR Model , 2018, Journal of Time Series Analysis.

[6]  Nadia Vozlyublennaia,et al.  Investor attention, index performance, and return predictability , 2014 .

[7]  E. Z. Chini.  Forecasting dynamically asymmetric fluctuations of the U.S. business cycle , 2018 .

[8]  David Coble,et al.  Now-Casting Building Permits with Google Trends , 2017 .

[9]  N. Askitas,et al.  Google Econometrics and Unemployment Forecasting , 2009, SSRN Electronic Journal.

[10]  Jeffrey C. Fuhrer,et al.  Does Consumer Sentiment Forecast Household Spending? If So, Why? , 1994 .

[11]  H. Veiga,et al.  Reexamining financial and economic predictability with new estimators of realized variance and variance risk premium , 2018 .

[12]  Persistence Heterogeneity Testing in Panels with Interactive Fixed Effects , 2018, Journal of Time Series Analysis.

[13]  I. Welch,et al.  A Comprehensive Look at the Empirical Performance of Equity Premium Prediction II , 2004, SSRN Electronic Journal.

[14]  H. Varian,et al.  Predicting the Present with Google Trends , 2009 .

[15]  Tom Engsted,et al.  Disappearing Money Illusion , 2018 .

[16]  Bryan T. Kelly,et al.  The Three-Pass Regression Filter: A New Approach to Forecasting Using Many Predictors , 2014 .

[17]  Allan Timmermann,et al.  Complete subset regressions , 2013 .

[18]  David E. Rapach,et al.  Forecasting US employment growth using forecast combining methods , 2008 .

[19]  Norman R. Swanson,et al.  Forecasting Financial and Macroeconomic Variables Using Data Reduction Methods: New Empirical Evidence , 2010 .

[20]  T. Teräsvirta,et al.  Models with multiplicative decomposition of conditional variances and correlations , 2018, Financial Mathematics, Volatility and Covariance Modelling.

[21]  C. De Mol,et al.  Forecasting Using a Large Number of Predictors: Is Bayesian Regression a Valid Alternative to Principal Components? , 2006, SSRN Electronic Journal.

[22]  Kim Christensen,et al.  The Realized Empirical Distribution Function of Stochastic Variance with Application to Goodness-of-Fit Testing , 2018, Journal of Econometrics.

[23]  Peter Reinhard Hansen,et al.  The Model Confidence Set , 2010 .

[24]  T. Andersen,et al.  Short-Term Market Risks Implied by Weekly Options , 2017 .

[25]  J. Stock,et al.  Forecasting Using Principal Components From a Large Number of Predictors , 2002 .

[26]  Juri Marcucci,et al.  The Predictive Power of Google Searches in Forecasting Unemployment , 2012 .

[27]  Zhi Da,et al.  In Search of Attention , 2009 .

[28]  L. Kilian,et al.  How Useful Is Bagging in Forecasting Economic Time Series? A Case Study of U.S. Consumer Price Inflation , 2008 .

[29]  D'Amuri Francesco,et al.  Predicting unemployment in short samples with internet job search query data , 2009 .

[30]  G. Mirone.  Cross-Sectional Noise Reduction and More Efficient Estimation of Integrated Variance , 2018 .

[31]  J. Bai,et al.  Forecasting economic time series using targeted predictors , 2008 .

[32]  George Kapetanios,et al.  Revisiting Useful Approaches to Data-Rich Macroeconomic Forecasting , 2009, Comput. Stat. Data Anal..

[33]  John G. Matsusaka,et al.  Consumer Confidence and Economic Fluctuations , 1995 .

[34]  K. Hadri,et al.  Diffusion copulas: Identification and estimation , 2020, Journal of Econometrics.

[35]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

[36]  S. Davis,et al.  Measuring Economic Policy Uncertainty , 2013 .

[37]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[38]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[39]  Torben G. Andersen,et al.  Consistent Inference for Predictive Regressions in Persistent VAR Economies , 2018 .

[40]  Torsten Schmidt,et al.  Forecasting Private Consumption: Survey-Based Indicators vs. Google Trends , 2009 .

[41]  Zhi Da,et al.  The Sum of All FEARS: Investor Sentiment and Asset Prices , 2013 .

[42]  David E. Rapach,et al.  Bagging or Combining (or Both)? An Analysis Based on Forecasting U.S. Employment Growth , 2010 .

[43]  J. Stock,et al.  Forecasting with Many Predictors , 2006 .

[44]  S. B. Thompson,et al.  Predicting Excess Stock Returns Out of Sample: Can Anything Beat the Historical Average? , 2008 .

[45]  Frédéric Karamé,et al.  Can Google Data Help Predict French Youth Unemployment , 2012 .

[46]  C. Christiansen,et al.  Forecasting US Recessions: The Role of Sentiment , 2013 .

[47]  Peter Molnár,et al.  Google Searches and Stock Returns , 2016 .

[48]  Emilio Zanetti Chini,et al.  Forecasters’ utility and forecast coherence , 2018 .

[49]  Zebin Yang,et al.  Online big data-driven oil consumption forecasting with Google trends , 2019, International Journal of Forecasting.

[50]  T. Teräsvirta,et al.  The shifting seasonal mean autoregressive model and seasonality in the Central England monthly temperature series, 1772–2016 , 2019, Econometrics and Statistics.

[51]  P. Burridge,et al.  Unit root tests in the presence of uncertainty about the non-stochastic trend , 2000 .

[52]  Ulrich Hounyo,et al.  Inference for Local Distributions at High Sampling Frequencies: A Bootstrap Approach , 2018, Journal of Econometrics.

[53]  Marco Lippi,et al.  The Generalized Dynamic Factor Model , 2002 .