Journal of the Korean Data and Information Science Society

The Korean Data and Information Science Society (한국데이터정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Forecasting algorithm using an improved genetic algorithm based on backpropagation neural network model

개선된 유전자 역전파 신경망에 기반한 예측 알고리즘

  • Yoon, YeoChang (Department of Information Security, Woosuk University) ;
  • Jo, Na Rae (Department of Information and Statistics, Chungbuk National University) ;
  • Lee, Sung Duck (Department of Information and Statistics, Chungbuk National University)
  • 윤여창 (우석대학교 정보보안학과) ;
  • 조나래 (충북대학교 정보통계학과) ;
  • 이성덕 (충북대학교 정보통계학과)
  • Received : 2017.10.20
  • Accepted : 2017.11.21
  • Published : 2017.11.30
⟨ Previous Next ⟩

Abstract

In this study, the problems in the short term stock market forecasting are analyzed and the feasibility of the ARIMA method and the backpropagation neural network is discussed. Neural network and genetic algorithm in short term stock forecasting is also examined. Since the backpropagation algorithm often falls into the local minima trap, we optimized the backpropagation neural network and established a genetic algorithm based on backpropagation neural network for forecasting model in order to achieve high forecasting accuracy. The experiments adopted the korea composite stock price index series to make prediction and provided corresponding error analysis. The results show that the genetic algorithm based on backpropagation neural network model proposed in this study has a significant improvement in stock price index series forecasting accuracy.

본 연구에서는 단기 예측을 위한 자기회귀누적이동평균모형, 역전파 신경망 및 유전자 알고리즘의 결합 적용에 대하여 논의하고 이를 통한 유전자-신경망 알고리즘의 효용성을 살펴본다. 일반적으로 역전파 알고리즘은 지역 최소값에 수렴될 수 있는 단점이 있기 때문에, 여기서는 예측 정확도를 높이기 위해 역전파 신경망 구조를 최적화하고 유전자 알고리즘을 결합한 유전자-신경망 알고리즘 기반 예측모형을 구축한다. 실험을 통한 오차 비교는 KOSPI 지수를 이용한다. 결과는 이 연구에서 제안된 유전자-신경망 모형이 역전파 신경망 모형과 비교할 때 예측 정확도에서 어느 정도 유의한 효율성을 보여주고자 한다.

Keywords

References

  1. Araujo, R. A. (2010). A hybrid intelligent morphological approach for stock market forecasting. Neural Processing Letters, 31, 195-217. https://doi.org/10.1007/s11063-010-9133-1
  2. Box, G. E. P. and Jenkins, G. (1970). Time series analysis forecasting and control, Holdel-Day, San Francisco.
  3. Demuth, H. and Beale, M. (2001). Neural network toolbox for use with MATLAB, TheMathWorks.
  4. Hwang, S. Y. (2014). Contemporary review on the bifurcating autoregressive models : Overview and perspectives. Journal of the Korean Data & Information Science Society, 25, 1137-1149. https://doi.org/10.7465/jkdi.2014.25.5.1137
  5. Jung, J. and Lee. S. (2016). Comparison study of SARIMA and ARGO models for influenza epidemics prediction. Journal of the Korean Data & Information Science Society, 27, 1075-1081. https://doi.org/10.7465/jkdi.2016.27.4.1075
  6. Luo, B., Chen, Y. and Jiang, W. (2016). Stock market forecasting algorithm based on improved neural network. 2016 Eighth International Conference on Measuring Technology and Mechatronics Automation, 628-631.
  7. Smith, M. (1993). Neural networks for statistical modeling, Van Nostrand Reinhold, New York.
  8. Song, J. (2016). A study on demand forecasting for Jeju-bound tourists by travel purpose using seasonal ARIMA-intervention model. Journal of the Korean Data & Information Science Society, 27, 725-732. https://doi.org/10.7465/jkdi.2016.27.3.725
  9. Yang, C. X. and Zhu, Y. F. (2007). Time series analysis using GA optimized neural networks. Third International Conference on Neural Computation, 270-276.
  10. Yoon, Y. (2008). A learning using GA optimized neural networks. Proceedings of KIPS, 15, 27-29.
  11. Yoon, Y. (2010). Time series forecasting based on genetic neural network. Proceedings of KIPS, 17, 1106-1108.
  12. Yoon, Y. and Lee, S. (2013). A comparison of the effects of optimization learning rates using a modified learning process for generalized neural network. The Korean Journal of Applied Statistics, 26, 847-856. https://doi.org/10.5351/KJAS.2013.26.5.847
  13. Wu, Y. and Zhang, L. (2002). The effect of initial weight, learning rate and regularization on generalization performance and efficiency. Proceedings on ICSP, 1191-1194.
  14. Xiaodong, Y. (2015). Selection of initial weights and thresholds based on the genetic algorithm with the optimized back-propagation neural network. 12th International Conference on Fuzzy Systems and Knowledge Discovery, 173-177.