Can unemployment forecasts based on Google Trends help government design better policies? An investigation based on Spain and Portugal

Mihaela Simionescu and Javier Cifuentes-Faura

Journal of Policy Modeling, 2022, vol. 44, issue 1, 1-21

Abstract: The Covid-19 pandemic has increased the unemployment issue and accelerated the digital transformation. Real-time data specific to ongoing revolution in applied economic analysis are increasingly demanded to anticipate changes in unemployment to improve decision-making. The aim of this paper is to test whether unemployment rate forecasts based on Google Trends data improve the predictions based only on macroeconomic indicators published with a longer time lag. The research has been carried out at the national level for Spain and Portugal, and the main novelty is the analysis of unemployment rate forecasts at the regional level for Spain using dynamic panel data models to implement the best policies to reduce unemployment. The keywords unemployment and job offers have been used in each language. The results obtained demonstrate the capacity of Google Trends data associated with unemployment to improve the predictions of unemployment rates in Spanish regions. Moreover, predictions based on Google Trends data at national level in Spain and Portugal are significantly more accurate than those based on autoregressive models for both countries.

Keywords: Google Trends; Unemployment; Inflation; Pandemic; Policy (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0161893821001101
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:jpolmo:v:44:y:2022:i:1:p:1-21

DOI: 10.1016/j.jpolmod.2021.09.011

Access Statistics for this article

Journal of Policy Modeling is currently edited by A. M. Costa

More articles in Journal of Policy Modeling from Elsevier
Bibliographic data for series maintained by Catherine Liu ().