The Journal of the Korea Contents Association (한국콘텐츠학회논문지)

The Korea Contents Association (한국콘텐츠학회)
권호 표지
DOI QR코드

DOI QR Code

Forecasting Short-Term KOSPI using Wavelet Transforms and Fuzzy Neural Network

웨이블릿 변환과 퍼지 신경망을 이용한 단기 KOSPI 예측

  • 신동근 (삼육대학교 컴퓨터학부) ;
  • 정경용 (상지대학교 컴퓨터정보공학부)
  • Received : 2011.03.29
  • Accepted : 2011.04.07
  • Published : 2011.06.28
Download PDF
⟨ Previous Next ⟩

Abstract

The methodology of KOSPI forecast has been considered as one of the most difficult problem to develop accurately since short-term KOSPI is correlated with various factors including politics and economics. In this paper, we presents a methodology for forecasting short-term trends of stock price for five days using the feature selection method based on a neural network with weighted fuzzy membership functions (NEWFM). The distributed non-overlap area measurement method selects the minimized number of input features by removing the worst input features one by one. A technical indicator are selected for preprocessing KOSPI data in the first step. In the second step, thirty-nine numbers of input features are produced by wavelet transforms. Twelve numbers of input features are selected as the minimized numbers of input features from thirty-nine numbers of input features using the non-overlap area distribution measurement method. The proposed method shows that sensitivity, specificity, and accuracy rates are 72.79%, 74.76%, and 73.84%, respectively.

KOSPI는 정치 및 경제를 포함한 다양한 요소에 영향을 받는 관계로 정확한 단기 KOSPI 예측 방법론 개발은 매우 어려운 문제로 여겨지고 있다. 본 논문에서는 가중 퍼지소속함수 기반 신경망(NEWFM; neural network with weighted fuzzy membership functions)의 특징 추출기법을 사용하여 5일 동안의 주가 단기추세를 예측하는 방안을 제안한다. 비중복면적 분산 측정법에 의해 중요도가 가장 낮은 특징입력을 하나씩 제거하면서 최소의 특징입력을 선택한다. 특징입력으로써 기술지표를 이용하여 얻은 데이터를 웨이블릿 변환을 이용하여 39개의 계수들을 추출한다. 이들 39개의 특징입력 중 비중복면적 분산측정법에 의해서 추출된 12개의 계수가 사용된다. 제안된 방법에서는 민감도가 72.79%, 특이도가 74.76%, 정확도가 73.84%를 나타낸다.

Keywords

References

  1. K. K. Ang and C. Quek, "Stock Trading Using RSPOP: A Novel Rough Set-Based Neuro-Fuzzy Approach," IEEE Trans. Neural Networks, Vol.17, No.5, pp.790-802, 2006. https://doi.org/10.1109/TNN.2006.875996
  2. J. S. Lim, "Finding Features for Real-Time Premature Ventricular Contraction Detection Using a Fuzzy Neural Network System," IEEE Trans. Neural Networks, Vol.20, Issue 3, pp.522-527, 2009. https://doi.org/10.1109/TNN.2008.2012031
  3. S. H. Chai and J. S. Lim, "Economic Turning Point Forecasting Using Fuzzy Neural Network and Non-Overlap Area Distribution Measurement Method," The Korean Economic Association, Vol.23, No.1, pp.111-130, 2007.
  4. T. V. Gestel, "Financial Time Series Prediction Using Least Squares Support Vector Machines Within the Evidence Framework," IEEE Trans. Neural Networks, Vol.12, No.4, pp.809-821, 2001. https://doi.org/10.1109/72.935093
  5. S-M Zhou and J. Q. Gan, "Constructing L2-SVM- Based Fuzzy Classifiers in High-Dimensional Space With Automatic Model Selection and Fuzzy Rule Ranking," IEEE Trans. on Fuzzy Systems, Vol.15, No.3, pp.398-409, 2007. https://doi.org/10.1109/TFUZZ.2006.882464
  6. T. Ray, H. Yenshan, and C. Charles, "Forecasting S&P 500 Stock Index Futures with a Hybrid AI System," Decision Support Systems, Vol.23, Issue 2, pp.161-174, 1998. https://doi.org/10.1016/S0167-9236(98)00028-1
  7. S. H. Lee, J. S. Lim, "KOSPI Time Series Analysis Using Neural Network with Weighted Fuzzy Membership Functions," LNAI 4953, pp.53-62, 2008.
  8. K. J. Kim, "Artificial Neural Networks with Evolutionary Instance Selection for Financial Forecasting," Expert Systems with Applications, Vol.30, Issue 3, pp.519-526, 2006. https://doi.org/10.1016/j.eswa.2005.10.007
  9. Q. Min "Predicting US Recession with Leading Indicators via Neural Network Models," International Journal of Forecasting, Vol.17, Issue 3, pp.383-401, 2001. https://doi.org/10.1016/S0169-2070(01)00092-9
  10. J. S. Lim, "Finding Fuzzy Rules by Neural Network with Weighted Fuzzy Membership Function," International Journal of Fuzzy Logic and Intelligent Systems, Vol.4, No.2, pp.211-216, 2004. https://doi.org/10.5391/IJFIS.2004.4.2.211
  11. K. J. Kim, "Financial Time Series Forecasting using Support Vector Machines," Neurocomputing, Vol.55, Issues 1-2, pp.307-309, 2003. https://doi.org/10.1016/S0925-2312(03)00372-2
  12. J. S. Lim, S. Gupta, "Feature Selection Using Weighted Neuro-Fuzzy Membership Functions," The International Conference on Artificial Intelligence, Vol.1, pp.1301-1315, Las Vegas, Nevada, 2004.
  13. S. A. George, P. V. Kimon, "Forecasting Stock Market Short-Term Trends using a Neuro-Fuzzy based Methodology," Expert Systems with Applications, Vol.36, Issue 7, pp.10696-10707, 2009 https://doi.org/10.1016/j.eswa.2009.02.043
  14. M. Suryanarayana, B. Darcy, "Analysis of Feed forward Backpropagation Neural Networks used in Vehicle Detection," Transportation Research Part C: Emerging Tech., Vol.3, Issue 3, pp.161-174, 1995. https://doi.org/10.1016/0968-090X(95)00004-3
  15. S. Mallat, "Zero Crossings of a Wavelet Transform," IEEE Trans. Inf. Theory, Vol. 37, No.4, pp.1019-1033, 1991. https://doi.org/10.1109/18.86995
  16. B. Scholkopf, A. J. Smola, R. C. Williamson, P. L. Bartlett, "New Support Vector Algorithms," Neural Computation, Vol.12, pp.1207-1245, 2000. https://doi.org/10.1162/089976600300015565
  17. 이은진, 민철홍, 김태선, "신경 회로망과 통계적 기법을 이용한 종합주가지수 예측 모형의 개발", 전자공학회 논문지, 제45권, 제5호, 2008.
  18. 이상홍, 임준식, "KOSPI 예측을 위한 NEWFM 기반의 특징입력 및 퍼지규칙 추출", 한국 인터넷정보학회 논문지, 제9권, 제1호, 2007.

Cited by

  1. Neuro-Fuzzy Network-based Depression Diagnosis Algorithm Using Optimal Features of HRV vol.12, pp.2, 2012, https://doi.org/10.5392/JKCA.2012.12.02.001