The industrial asymmetry of the stock price prediction with investor sentiment: Based on the comparison of predictive effects with SVR

• Author: Lin Lai,Yi Sun,Zhenni Jin,Zhewen Liao,Kun Guo
• Date: 01 November 2020
• Published date: 01 November 2020
• DOI: http://doi.org/10.1002/for.2681

RESEARCH ARTICLE

The industrial asymmetry of the stock price prediction with

investor sentiment: Based on the comparison of predictive

effects with SVR

Zhenni Jin

1,3,4

| Kun Guo

2,3,4

| Yi Sun

2

| Lin Lai

5

| Zhewen Liao

2,3,4

1

Sino-Danish College, University of

Chinese Academy of Science, Beijing,

China

2

School of Economics and Management,

University of Chinese Academy of

Science, Beijing, China

3

Research Center on Fictitious Economy

and Data Science, Chinese Academy of

Science, Beijing, China

4

Key Laboratory of Big Data Mining and

Knowledge Management, Chinese

Academy of Science, Beijing, China

5

HSBC Business School, Peking

University, Shenzhen, China

Correspondence

Kun Guo and Yi Sun, School of

Economics and Management, University

of Chinese Academy of Sciences, Beijing

100,190, China.

Email: guokun@ucas.ac.cn; suny@ucas.

ac.cn

Funding information

National Natural Science Foundation of

China, Grant/Award Numbers: 71501175,

71673265

Abstract

As a representative emerging financial market, the Chinese stock market is

more prone to volatility because of investor sentiment. It is reasonable to use

efficient predictive methods to analyze the influence of investor sentiment on

stock price forecasting. This paper conducts a comparative study about the pre-

dictive performance of artificial neural network, support vector regression

(SVR) and autoregressive integrated moving average and selects SVR to study

the asymmetry effect of investor sentiment on different industry index predic-

tions. After studying the relevant financial indicators, the results divide the

Shenwan first-class industries into two types and show that the industries

affected by investor sentiment are composed of young companies with high

growth and high operative pressure and there are a great number of invest-

ment bubbles in those companies.

KEYWORDS

industries asymmetry, investor sentiment, stock price prediction, SVR

1|INTRODUCTION

With the rapid development of the financial industry,

stock prediction has become increasingly attractive for

different agents in stock markets. The sentiment of indi-

vidual investors, as one important agent in the market,

plays an increasingly important role in the stock price

movements. A growing number of studies showed that

investor sentiment can be used to predict the stock vola-

tility to some extent. However, facing the challenges from

the poor performance of the efficient market hypothesis,

considerable attention has been paid to exploring effi-

cient methods for forecasting stock market behavior.

For some years, machine learning techniques have

been widely implemented in predicting stock markets.

Some studies have found that artificial neural network

(ANN) has successfully built prediction models to predict

financial time series (Cheng, Wagner, & Lin, 1996;

Sharda & Patil, 1992; Van & Robert, 1997). Hamid and

Iqbal (2004) applied ANN and the Barone-Adesi and

Whaley (BAW) American futures options pricing model

to forecast volatility of the S&P 500 index futures prices.

They found that predictions from neural networks

outperform the financial time series model. Adebiyi,

Adewumi, and Ayo (2014) employed the stock data from

the New York Stock Exchange to test the predicting

Received: 14 February 2019 Revised: 9 December 2019 Accepted: 18 March 2020

DOI: 10.1002/for.2681

1166 © 2020 John Wiley & Sons, Ltd. Journal of Forecasting. 2020;39:1166–1178.wileyonlinelibrary.com/journal/for