A MIDAS modelling framework for Chinese inflation index forecast incorporating Google search data

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

29 Scopus Citations
View graph of relations


  • Xin Li
  • Wei Shang
  • Shouyang Wang
  • Jian Ma

Related Research Unit(s)


Original languageEnglish
Article number593
Pages (from-to)112-125
Journal / PublicationElectronic Commerce Research and Applications
Issue number2
Online published9 Jan 2015
Publication statusPublished - Mar 2015


Increased internet penetration makes it possible for user generated content (UGC) to reflect people's insights and expectations on economic activities. As representative and easily accessible UGC data that reflect public opinions on economic issues, Google search data have been used to forecast macroeconomic indicators in existing literatures. However, very little empirical research has directly used Google search data to improve the forecast accuracy. This paper proposes an integrated framework, which constructs keywords base and extracts search data accordingly, and then incorporates the search data into a mixed data sampling (MIDAS) model. Five groups of search data are extracted based on the constructed keywords and are then used in MIDAS model to forecast Chinese consumer price index (CPI) from 2004 to 2012. The empirical results indicate that the search data are strongly correlated with CPI, which is officially released by the Statistic Bureau of China; the MIDAS model including the search data outperforms the benchmark models, with the average reduction of root mean square error (RMSE) being 32.9%. This research provides a rigorous and generalizable framework for macroeconomic trend prediction using Google search data, and would have great potential in supporting business decisions by eliciting relevant information from UGC data in the Internet. 2015 Elsevier B.V. All rights reserved.

Research Area(s)

  • Consumer price index, Google search data, Inflation index forecast, MIDAS modelling framework, User generated content