Forecasting Chinese GDP Using Online Data

Taoxiong Liu, Xiaofei Xu and Fangda Fan

Emerging Markets Finance and Trade, 2018, vol. 54, issue 4, 733-746

Abstract: Because big data are widely used today, whether and how to use big data in macroeconomic forecasting has become a new field of economic research. In macroeconomic analyses, two types of data can be applied, namely, structured data and unstructured information. Statistical government data are well-structured, whereas Internet search behavior information, which is representative of online data, is unstructured. This article explores whether Internet search behavior information can facilitate the forecasting of macroeconomic aggregates and components and analyzes the use of feasible methods of structured data and unstructured information. This study is based on the macroeconomic forecasting model and verifies the effect of the two-step method. We find that Internet search behavior information can help forecast the macro economy, and we determine that the best method for variable selection using structured and unstructured data is the two-step method. First, only statistical government data are used, and temporary optimal models are selected. Second, Internet search behavior information are added to these models, and the optimal model is then determined.

Date: 2018
References: Add references at CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
http://hdl.handle.net/10.1080/1540496X.2016.1216841 (text/html)
Access to full text is restricted to subscribers.

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:mes:emfitr:v:54:y:2018:i:4:p:733-746

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/MREE20

DOI: 10.1080/1540496X.2016.1216841

Access Statistics for this article

More articles in Emerging Markets Finance and Trade from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().