Forecasting the Dynamic Correlation of Stock Indices Based on Deep Learning Method

Jian Ni () and Yue Xu ()
Additional contact information
Jian Ni: Southwestern University of Finance and Economics
Yue Xu: Southwestern University of Finance and Economics

Computational Economics, 2023, vol. 61, issue 1, No 2, 35-55

Abstract: Abstract With the economic globalization, it is important to accurately estimate and predict the correlation between global stock markets for the efficient asset allocation around the globe. While practitioners may resort to various GARCH-type models for correlation forecasting, the forecasting accuracy is still not very satisfactory. For the first time, this paper introduces a deep learning method into the research of stock market correlation. A hybrid DCDNN model is developed based on the RDNN (recurrent deep neural network) and DCC-GARCH models. Deep learning is then devised to forecast the prediction error of the DCC-GARCH model in order to improve the prediction accuracy of stock market correlation. An autoencoder is also introduced in the empirical study to extract useful features of the stock index data. Then, the correlations among the stock markets in China, Hong Kong, the United States and Europe are predicted and tested. We show that the accuracy of the DCDNN model is significantly higher than that of the DCC-GARCH model. The results indicate that the introduction of deep learning can help improve the efficacy of existing correlation forecasting methods.

Keywords: Correlation forecasting; Stock market; Deep learning; DCC-GARCH; Autoencoder (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: Track citations by RSS feed

Downloads: (external link)
http://link.springer.com/10.1007/s10614-021-10198-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:kap:compec:v:61:y:2023:i:1:d:10.1007_s10614-021-10198-3

Ordering information: This journal article can be ordered from
http://www.springer. ... ry/journal/10614/PS2

DOI: 10.1007/s10614-021-10198-3

Access Statistics for this article

Computational Economics is currently edited by Hans Amman

More articles in Computational Economics from Springer, Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().