Empirical analysis : stock market prediction via extreme learning machine

Xiaodong LI, Haoran XIE, Ran WANG, Yi CAI*, Jingjing CAO, Feng WANG, Huaqing MIN, Xiaotie DENG

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)

31 Citations (Scopus)

Abstract

How to predict stock price movements based on quantitative market data modeling is an attractive topic. In front of the market news and stock prices that are commonly believed as two important market data sources, how to extract and exploit the hidden information within the raw data and make both accurate and fast predictions simultaneously becomes a challenging problem. In this paper, we present the design and architecture of our trading signal mining platform that employs extreme learning machine (ELM) to make stock price prediction based on those two data sources concurrently. Comprehensive experimental comparisons between ELM and the state-of-the-art learning algorithms, including support vector machine (SVM) and back-propagation neural network (BP-NN), have been undertaken on the intra-day tick-by-tick data of the H-share market and contemporaneous news archives. The results have shown that (1) both RBF ELM and RBF SVM achieve higher prediction accuracy and faster prediction speed than BP-NN; (2) the RBF ELM achieves similar accuracy with the RBF SVM and (3) the RBF ELM has faster prediction speed than the RBF SVM. Simulations of a preliminary trading strategy with the signals are conducted. Results show that strategy with more accurate signals will make more profits with less risk.

Original languageEnglish
Pages (from-to)67-78
Number of pages12
JournalNeural Computing and Applications
Volume27
Issue number1
Early online date2 Feb 2014
DOIs
Publication statusPublished - Jan 2016
Externally publishedYes

Fingerprint

Learning systems
Support vector machines
Backpropagation
Neural networks
Learning algorithms
Data structures
Profitability
Financial markets

Bibliographical note

This work was partly supported by National Natural Science Foundation of China (Grant No. 61300137); the Guangdong Natural Science Foundation, China (Grant No. S2011040002222); the Fundamental Research Funds for the Central Universities, SCUT (Grant No. 2012ZM0077). This work was also supported by Shenzhen New Industry Development Fund under grant No. JCYJ20120617120716224.

Keywords

  • Extreme learning machine
  • Stock market prediction
  • Trading signal mining platform

Cite this

LI, Xiaodong ; XIE, Haoran ; WANG, Ran ; CAI, Yi ; CAO, Jingjing ; WANG, Feng ; MIN, Huaqing ; DENG, Xiaotie. / Empirical analysis : stock market prediction via extreme learning machine. In: Neural Computing and Applications. 2016 ; Vol. 27, No. 1. pp. 67-78.
@article{6023a7c611fc4c6483db28213f0944b5,
title = "Empirical analysis : stock market prediction via extreme learning machine",
abstract = "How to predict stock price movements based on quantitative market data modeling is an attractive topic. In front of the market news and stock prices that are commonly believed as two important market data sources, how to extract and exploit the hidden information within the raw data and make both accurate and fast predictions simultaneously becomes a challenging problem. In this paper, we present the design and architecture of our trading signal mining platform that employs extreme learning machine (ELM) to make stock price prediction based on those two data sources concurrently. Comprehensive experimental comparisons between ELM and the state-of-the-art learning algorithms, including support vector machine (SVM) and back-propagation neural network (BP-NN), have been undertaken on the intra-day tick-by-tick data of the H-share market and contemporaneous news archives. The results have shown that (1) both RBF ELM and RBF SVM achieve higher prediction accuracy and faster prediction speed than BP-NN; (2) the RBF ELM achieves similar accuracy with the RBF SVM and (3) the RBF ELM has faster prediction speed than the RBF SVM. Simulations of a preliminary trading strategy with the signals are conducted. Results show that strategy with more accurate signals will make more profits with less risk.",
keywords = "Extreme learning machine, Stock market prediction, Trading signal mining platform",
author = "Xiaodong LI and Haoran XIE and Ran WANG and Yi CAI and Jingjing CAO and Feng WANG and Huaqing MIN and Xiaotie DENG",
note = "This work was partly supported by National Natural Science Foundation of China (Grant No. 61300137); the Guangdong Natural Science Foundation, China (Grant No. S2011040002222); the Fundamental Research Funds for the Central Universities, SCUT (Grant No. 2012ZM0077). This work was also supported by Shenzhen New Industry Development Fund under grant No. JCYJ20120617120716224.",
year = "2016",
month = "1",
doi = "10.1007/s00521-014-1550-z",
language = "English",
volume = "27",
pages = "67--78",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",
number = "1",

}

Empirical analysis : stock market prediction via extreme learning machine. / LI, Xiaodong; XIE, Haoran; WANG, Ran; CAI, Yi; CAO, Jingjing; WANG, Feng; MIN, Huaqing; DENG, Xiaotie.

In: Neural Computing and Applications, Vol. 27, No. 1, 01.2016, p. 67-78.

Research output: Journal PublicationsJournal Article (refereed)

TY - JOUR

T1 - Empirical analysis : stock market prediction via extreme learning machine

AU - LI, Xiaodong

AU - XIE, Haoran

AU - WANG, Ran

AU - CAI, Yi

AU - CAO, Jingjing

AU - WANG, Feng

AU - MIN, Huaqing

AU - DENG, Xiaotie

N1 - This work was partly supported by National Natural Science Foundation of China (Grant No. 61300137); the Guangdong Natural Science Foundation, China (Grant No. S2011040002222); the Fundamental Research Funds for the Central Universities, SCUT (Grant No. 2012ZM0077). This work was also supported by Shenzhen New Industry Development Fund under grant No. JCYJ20120617120716224.

PY - 2016/1

Y1 - 2016/1

N2 - How to predict stock price movements based on quantitative market data modeling is an attractive topic. In front of the market news and stock prices that are commonly believed as two important market data sources, how to extract and exploit the hidden information within the raw data and make both accurate and fast predictions simultaneously becomes a challenging problem. In this paper, we present the design and architecture of our trading signal mining platform that employs extreme learning machine (ELM) to make stock price prediction based on those two data sources concurrently. Comprehensive experimental comparisons between ELM and the state-of-the-art learning algorithms, including support vector machine (SVM) and back-propagation neural network (BP-NN), have been undertaken on the intra-day tick-by-tick data of the H-share market and contemporaneous news archives. The results have shown that (1) both RBF ELM and RBF SVM achieve higher prediction accuracy and faster prediction speed than BP-NN; (2) the RBF ELM achieves similar accuracy with the RBF SVM and (3) the RBF ELM has faster prediction speed than the RBF SVM. Simulations of a preliminary trading strategy with the signals are conducted. Results show that strategy with more accurate signals will make more profits with less risk.

AB - How to predict stock price movements based on quantitative market data modeling is an attractive topic. In front of the market news and stock prices that are commonly believed as two important market data sources, how to extract and exploit the hidden information within the raw data and make both accurate and fast predictions simultaneously becomes a challenging problem. In this paper, we present the design and architecture of our trading signal mining platform that employs extreme learning machine (ELM) to make stock price prediction based on those two data sources concurrently. Comprehensive experimental comparisons between ELM and the state-of-the-art learning algorithms, including support vector machine (SVM) and back-propagation neural network (BP-NN), have been undertaken on the intra-day tick-by-tick data of the H-share market and contemporaneous news archives. The results have shown that (1) both RBF ELM and RBF SVM achieve higher prediction accuracy and faster prediction speed than BP-NN; (2) the RBF ELM achieves similar accuracy with the RBF SVM and (3) the RBF ELM has faster prediction speed than the RBF SVM. Simulations of a preliminary trading strategy with the signals are conducted. Results show that strategy with more accurate signals will make more profits with less risk.

KW - Extreme learning machine

KW - Stock market prediction

KW - Trading signal mining platform

UR - http://www.scopus.com/inward/record.url?scp=84953347190&partnerID=8YFLogxK

U2 - 10.1007/s00521-014-1550-z

DO - 10.1007/s00521-014-1550-z

M3 - Journal Article (refereed)

AN - SCOPUS:84953347190

VL - 27

SP - 67

EP - 78

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 1

ER -