Does High-Frequency Social Media Data Improve Forecasts of Low-Frequency Consumer Confidence Measures?*

Regression Models with Mixed Sampling Frequencies

Steven Lehrer (), Tian Xie and Tao Zeng

Journal of Financial Econometrics, 2021, vol. 19, issue 5, 910-933

Abstract: Social media data present challenges for forecasters since one must convert text into data and deal with issues related to these measures being collected at different frequencies and volumes than traditional financial data. In this article, we use a deep learning algorithm to measure sentiment within Twitter messages on an hourly basis and introduce a new method to undertake mixed data sampling (MIDAS) that allows for a weaker discounting of historical data that is well-suited for this new data source. To evaluate the performance of approach relative to alternative MIDAS strategies, we conduct an out of sample forecasting exercise for the consumer confidence index with both traditional econometric strategies and machine learning algorithms. Irrespective of the estimator used to conduct forecasts, our results show that (i) including consumer sentiment measures from Twitter greatly improves forecast accuracy and (ii) there are substantial gains from our proposed MIDAS procedure relative to common alternatives.

Keywords: big data; forecasting; machine learning; MIDAS; social media (search for similar items in EconPapers)
JEL-codes: C53 E27 G17 (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
http://hdl.handle.net/10.1093/jjfinec/nbz037 (application/pdf)
Access to full text is restricted to subscribers.

Related works:
Working Paper: Does High Frequency Social Media Data Improve Forecasts of Low Frequency Consumer Confidence Measures? (2019)
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:oup:jfinec:v:19:y:2021:i:5:p:910-933.

Ordering information: This journal article can be ordered from
https://academic.oup.com/journals

Access Statistics for this article

Journal of Financial Econometrics is currently edited by Allan Timmermann and Fabio Trojani

More articles in Journal of Financial Econometrics from Oxford University Press Oxford University Press, Great Clarendon Street, Oxford OX2 6DP, UK. Contact information at EDIRC.
Bibliographic data for series maintained by Oxford University Press ().