ePrints

The Fluctuation Correlation between Investor Sentiment and Stock Index Using VMD-LSTM: Evidence from China Stock Market

Lookup NU author(s): Dr Jie ZhangORCiD

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.

Abstract

The impact of the investor sentiment on China’s capital market price volatility is concerned underthe perspective of the behavioral finance. Firstly, in terms of the existing methods of establishingthe investor sentiment index, the composite investor sentiment index which include six indicators(five objective indicators and a subjective indicator) are obtained. Secondly, VMD-LSTM (VariationalMode Decomposition and Long Short Term Memory) hybrid neural network model is usedto decompose and restructure the investor sentiment index and the Shanghai Security ExchangeComposite Index (SSEC) into the short-term, medium-term and long-term trend. Each trend istrained to obtain the forecasting results in three different time scales, and then to achieve the finalpredicting results by superimposing the output of each trend. Furthermore, compare with otherprediction methods, the model can indeed improve the overall predicting accuracy. Finally,GARCH model and the co-integration error regression model are used to discuss the fluctuationcorrelation and VAR (Vector Auto-regression) models are established to analyze the causalitybetween the stock market indices and the investor sentiment index.

Publication metadata

Author(s): Gao Z, Zhang J

Publication type: Article

Publication status: Published

Journal: North American Journal of Finance and Economics

Year: 2023

Volume: 66

Print publication date: 01/05/2023

Online publication date: 31/03/2023

Acceptance date: 30/03/2023

ISSN (print): 1062-9408

ISSN (electronic): 1879-0860

Publisher: Elsevier

URL: https://doi.org/10.1016/j.najef.2023.101915

DOI: 10.1016/j.najef.2023.101915

Altmetrics

Share