A Novel Decomposition-Ensemble Approach for Forecasting Stock Price With Quantum Neural Network and Big Data

Aug 27, 2026

Uploaded by Ivy

Stock price forecasting remains a demanding task for market regulators, financial practitioners, and individual investors, motivating continual model improvement. This study develops a novel decomposition-ensemble framework that integrates multivariate empirical mode decomposition with a quantum neural network to raise predictive accuracy. It encodes investor anticipation, attention, and sentiment using multi-source big data from stock markets, search engines, and social media, then conducts empirical analysis with Shenzhen Stock Exchange daily average prices. Results show superior performance over benchmark models, supporting forecasting of highly volatile, nonlinear stock series.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages24

Reading Time1 h 0 min

AccessFree to download

Introduction

Journal of Forecasting RESEARCH ARTICLE A Novel Decomposition-Ensemble Approach for Forecasting Stock Price With Quantum Neural Network and Big Data Shuihan Liu1,2 | Gang Xie3 1Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China | 2School of Mathematical Sciences & School of Economics and Management, University of Chinese Academy of Sciences, Beijing, China | 3School of Computer and Artificial Intelligence, Beijing Technology and Business University, China Correspondence: Gang Xie ([gxie@amss.ac.cn](gxie@amss.ac.cn)) Received: 17 August 2023 | Revised: 3 April 2024 | Accepted: 29 September 2025 Funding: This work was supported by This research was funded by National Natural Science Foundation of China (No. 72271228, 72041029, 71988101, 71771207) and the Project of BTBU High Level Talent Team Construction. Keywords: big data | decomposition-ensemble methodology | multivariate empirical mode decomposition | quantum neural network | stock price forecasting ABSTRACT Stock price forecasting has always been a classic and challenging task, attracting widespread attention from stakeholders such as market regulators, financial practitioners, and individual investors. Developing new models to improve the accuracy of stock price forecasting is also a persistent goal pursued by researchers. In recent years, quantum computing has developed rapidly. The emergence of quantum machine learning (QML) and quantum neural network (QNN) models has made it possible to develop new stock price forecasting models that leverage the advantages of quantum algorithms. To improve predictive accuracy, this study proposes a novel decomposition-ensemble approach based on multivariate empirical mode decomposition and QNN. In the prediction, multi-source big data from the stock market, search engines, and social media are employed to represent investor anticipation, attention, and sentiments, respectively. Using the daily average stock price in the Shenzhen Stock Exchange, an empirical analysis is conducted to illustrate the proposed approach. The results suggest that the proposed approach outperforms benchmark models, indicating that it is a promising method for forecasting stock price series with high volatility and nonlinearity. 1 | Introduction According to data from the World Federation of Exchanges (WFE) and the Securities Industry and Financial Markets Association (SIFMA), global stock markets have experienced rapid expansion in the past two decades, with their value increasing threefold by 2023. In particular, the Chinese stock market surged from 5 trillion yuan in 2000 to over 90 trillion yuan in 2022. The Shanghai and Shenzhen Stock Exchanges are the two major exchanges in China, ranking second in the total market value of listed companies worldwide. Compared with the Shanghai Stock Exchange, the Shenzhen Stock Exchange includes the growth enterprise market (GEM) and small and medium enterprise (SME) board markets, which have a larger number of listed companies, higher stock trading activity, and higher price-to-earnings ratios, attracting high attention from the academic community. Due to the fact that stock prices are a direct reflection of the financial market, many scholars are interested in the overall market valuation level of the Shenzhen Stock Exchange market. Accurately predicting stock prices is crucial, as stock prices are one of the most closely monitored indicators by market regulators, financial experts, and investors. The purpose of this article is to improve the predictive accuracy of the average stock price of the Shenzhen Stock Exchange market in order to help stakeholders more accurately evaluate market conditions and make decisions in the real world. © 2025 John Wiley & Sons Ltd. Journal of Forecasting, 2026; 45:391–414 391 [https://doi.org/10.1002/for.70047](https://doi.org/10.1002/for.70047) In the literature related to stock price forecasting, fundamental ana

FAQs

What modeling approach does the study propose for stock price forecasting?

It proposes a novel decomposition-ensemble approach that combines multivariate empirical mode decomposition with a quantum neural network to improve prediction accuracy.

Which data sources are used to represent investor behavior signals?

Multi-source big data are used: stock market data, search engine information, and social media signals are mapped to investor anticipation, attention, and sentiments.

What empirical dataset and results are reported?

The method is tested using the daily average stock price in the Shenzhen Stock Exchange, and it outperforms benchmark models, indicating promise for volatile and nonlinear stock series forecasting.

Aug 27, 2026

Uploaded by Ivy