L-GEM based MCS aided candlestick pattern investment strategy in the Shenzhen stock market

Wei XIAO, W. Y., Wing NG, Michael Arthur FIRTH, Daniel S. YEUNG, Gao Yang CAI, Jin Cheng LI, Bin Bin SUN

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

5 Citations (Scopus)

Abstract

An integral part of China's economic reforms is the privatization of state-owned enterprises (SOEs) and listing the profitable units of the SOEs on the stock market. The two stock exchanges in Shanghai and Shenzhen were opened nearly twenty years ago. The Shenzhen stock exchange market is young and energetic. Moreover, it practices a T+1 settlement rule instead of real time trade as in Hong Kong or other exchange markets. One important research question is whether there are patterns that can be identified in stock prices that can be used to develop profitable investment strategies. If strategies can be found, then this represents a violation of the efficient market hypothesis. In this work, we propose an investment strategy by using Radial Basis Function Neural Networks (RBFNN) trained by Localized Generalization Error Model (L-GEM) and 4 stock price candlestick patterns. Every base RBFNN in the Multiple Classifier System (MCS) recognizes the occurrence of a particular candlestick pattern and the MCS combines opinions from the 4 base RBFNNs by a weighted sum to provide a final prediction. If the MCS predicts an increase for the next day, it will buy the stock and sell it within three days whenever the opening price is higher than the buy-in price or else after three days have passed. Experimental results with stocks in Shenzhen market show that our investment strategy statistically significantly outperforms a random investment, i.e. the EMH is invalid in this case.
Original languageEnglish
Title of host publicationProceedings of the 2009 International Conference on Machine Learning and Cybernetics
PublisherIEEE
Pages243-248
Number of pages6
DOIs
Publication statusPublished - 1 Jan 2009

Fingerprint

Investment strategy
Stock market
Classifier
Shenzhen
State-owned enterprises
Radial basis function
Neural networks
Stock exchange
Stock prices
Integral
Prediction
Privatization
Efficient market hypothesis
Shanghai
Violations
Hong Kong
China
Economic reform

Bibliographical note

Paper presented at the 8th International Conference on Machine Learning and Cybernetics, Jul 12-15, 2009, Baoding, China.
ISBN of the source publication: 9781424447053

Keywords

  • Candlestick pattern
  • EMH
  • L-GEM
  • RBFNN
  • Shenzhen Stock

Cite this

XIAO, W., NG, W. Y. . W., FIRTH, M. A., YEUNG, D. S., CAI, G. Y., LI, J. C., & SUN, B. B. (2009). L-GEM based MCS aided candlestick pattern investment strategy in the Shenzhen stock market. In Proceedings of the 2009 International Conference on Machine Learning and Cybernetics (pp. 243-248). IEEE. https://doi.org/10.1109/ICMLC.2009.5212499
XIAO, Wei ; NG, W. Y., Wing ; FIRTH, Michael Arthur ; YEUNG, Daniel S. ; CAI, Gao Yang ; LI, Jin Cheng ; SUN, Bin Bin. / L-GEM based MCS aided candlestick pattern investment strategy in the Shenzhen stock market. Proceedings of the 2009 International Conference on Machine Learning and Cybernetics. IEEE, 2009. pp. 243-248
@inproceedings{8fb42cd594904d03bd175845b55bb5c7,
title = "L-GEM based MCS aided candlestick pattern investment strategy in the Shenzhen stock market",
abstract = "An integral part of China's economic reforms is the privatization of state-owned enterprises (SOEs) and listing the profitable units of the SOEs on the stock market. The two stock exchanges in Shanghai and Shenzhen were opened nearly twenty years ago. The Shenzhen stock exchange market is young and energetic. Moreover, it practices a T+1 settlement rule instead of real time trade as in Hong Kong or other exchange markets. One important research question is whether there are patterns that can be identified in stock prices that can be used to develop profitable investment strategies. If strategies can be found, then this represents a violation of the efficient market hypothesis. In this work, we propose an investment strategy by using Radial Basis Function Neural Networks (RBFNN) trained by Localized Generalization Error Model (L-GEM) and 4 stock price candlestick patterns. Every base RBFNN in the Multiple Classifier System (MCS) recognizes the occurrence of a particular candlestick pattern and the MCS combines opinions from the 4 base RBFNNs by a weighted sum to provide a final prediction. If the MCS predicts an increase for the next day, it will buy the stock and sell it within three days whenever the opening price is higher than the buy-in price or else after three days have passed. Experimental results with stocks in Shenzhen market show that our investment strategy statistically significantly outperforms a random investment, i.e. the EMH is invalid in this case.",
keywords = "Candlestick pattern, EMH, L-GEM, RBFNN, Shenzhen Stock",
author = "Wei XIAO and NG, {W. Y., Wing} and FIRTH, {Michael Arthur} and YEUNG, {Daniel S.} and CAI, {Gao Yang} and LI, {Jin Cheng} and SUN, {Bin Bin}",
note = "Paper presented at the 8th International Conference on Machine Learning and Cybernetics, Jul 12-15, 2009, Baoding, China. ISBN of the source publication: 9781424447053",
year = "2009",
month = "1",
day = "1",
doi = "10.1109/ICMLC.2009.5212499",
language = "English",
pages = "243--248",
booktitle = "Proceedings of the 2009 International Conference on Machine Learning and Cybernetics",
publisher = "IEEE",

}

XIAO, W, NG, WYW, FIRTH, MA, YEUNG, DS, CAI, GY, LI, JC & SUN, BB 2009, L-GEM based MCS aided candlestick pattern investment strategy in the Shenzhen stock market. in Proceedings of the 2009 International Conference on Machine Learning and Cybernetics. IEEE, pp. 243-248. https://doi.org/10.1109/ICMLC.2009.5212499

L-GEM based MCS aided candlestick pattern investment strategy in the Shenzhen stock market. / XIAO, Wei; NG, W. Y., Wing; FIRTH, Michael Arthur; YEUNG, Daniel S.; CAI, Gao Yang; LI, Jin Cheng; SUN, Bin Bin.

Proceedings of the 2009 International Conference on Machine Learning and Cybernetics. IEEE, 2009. p. 243-248.

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

TY - GEN

T1 - L-GEM based MCS aided candlestick pattern investment strategy in the Shenzhen stock market

AU - XIAO, Wei

AU - NG, W. Y., Wing

AU - FIRTH, Michael Arthur

AU - YEUNG, Daniel S.

AU - CAI, Gao Yang

AU - LI, Jin Cheng

AU - SUN, Bin Bin

N1 - Paper presented at the 8th International Conference on Machine Learning and Cybernetics, Jul 12-15, 2009, Baoding, China. ISBN of the source publication: 9781424447053

PY - 2009/1/1

Y1 - 2009/1/1

N2 - An integral part of China's economic reforms is the privatization of state-owned enterprises (SOEs) and listing the profitable units of the SOEs on the stock market. The two stock exchanges in Shanghai and Shenzhen were opened nearly twenty years ago. The Shenzhen stock exchange market is young and energetic. Moreover, it practices a T+1 settlement rule instead of real time trade as in Hong Kong or other exchange markets. One important research question is whether there are patterns that can be identified in stock prices that can be used to develop profitable investment strategies. If strategies can be found, then this represents a violation of the efficient market hypothesis. In this work, we propose an investment strategy by using Radial Basis Function Neural Networks (RBFNN) trained by Localized Generalization Error Model (L-GEM) and 4 stock price candlestick patterns. Every base RBFNN in the Multiple Classifier System (MCS) recognizes the occurrence of a particular candlestick pattern and the MCS combines opinions from the 4 base RBFNNs by a weighted sum to provide a final prediction. If the MCS predicts an increase for the next day, it will buy the stock and sell it within three days whenever the opening price is higher than the buy-in price or else after three days have passed. Experimental results with stocks in Shenzhen market show that our investment strategy statistically significantly outperforms a random investment, i.e. the EMH is invalid in this case.

AB - An integral part of China's economic reforms is the privatization of state-owned enterprises (SOEs) and listing the profitable units of the SOEs on the stock market. The two stock exchanges in Shanghai and Shenzhen were opened nearly twenty years ago. The Shenzhen stock exchange market is young and energetic. Moreover, it practices a T+1 settlement rule instead of real time trade as in Hong Kong or other exchange markets. One important research question is whether there are patterns that can be identified in stock prices that can be used to develop profitable investment strategies. If strategies can be found, then this represents a violation of the efficient market hypothesis. In this work, we propose an investment strategy by using Radial Basis Function Neural Networks (RBFNN) trained by Localized Generalization Error Model (L-GEM) and 4 stock price candlestick patterns. Every base RBFNN in the Multiple Classifier System (MCS) recognizes the occurrence of a particular candlestick pattern and the MCS combines opinions from the 4 base RBFNNs by a weighted sum to provide a final prediction. If the MCS predicts an increase for the next day, it will buy the stock and sell it within three days whenever the opening price is higher than the buy-in price or else after three days have passed. Experimental results with stocks in Shenzhen market show that our investment strategy statistically significantly outperforms a random investment, i.e. the EMH is invalid in this case.

KW - Candlestick pattern

KW - EMH

KW - L-GEM

KW - RBFNN

KW - Shenzhen Stock

UR - http://commons.ln.edu.hk/sw_master/7242

U2 - 10.1109/ICMLC.2009.5212499

DO - 10.1109/ICMLC.2009.5212499

M3 - Conference paper (refereed)

SP - 243

EP - 248

BT - Proceedings of the 2009 International Conference on Machine Learning and Cybernetics

PB - IEEE

ER -

XIAO W, NG WYW, FIRTH MA, YEUNG DS, CAI GY, LI JC et al. L-GEM based MCS aided candlestick pattern investment strategy in the Shenzhen stock market. In Proceedings of the 2009 International Conference on Machine Learning and Cybernetics. IEEE. 2009. p. 243-248 https://doi.org/10.1109/ICMLC.2009.5212499