DOI QR코드

DOI QR Code

Using Evolutionary Optimization to Support Artificial Neural Networks for Time-Divided Forecasting: Application to Korea Stock Price Index

Oh, Kyong Joo

  • 발행 : 2003.04.01

초록

This study presents the time-divided forecasting model to integrate evolutionary optimization algorithm and change point detection based on artificial neural networks (ANN) for the prediction of (Korea) stock price index. The genetic algorithm(GA) is introduced as an evolutionary optimization method in this study. The basic concept of the proposed model is to obtain intervals divided by change points, to identify them as optimal or near-optimal change point groups, and to use them in the forecasting of the stock price index. The proposed model consists of three phases. The first phase detects successive change points. The second phase detects the change-point groups with the GA. Finally, the third phase forecasts the output with ANN using the GA. This study examines the predictability of the proposed model for the prediction of stock price index.

키워드

Genetic Algorithms;Artificial Neural Networks;Change-Point Detection;Stock Price Index

참고문헌

  1. Communications in Statististics v.18 pp.3117-3134 An U-I approach to retrospective testing for shift parameters in a linear model Hawkins, D.L. https://doi.org/10.1080/03610928908830081
  2. Journal of Forecasting v.9 pp.527-529 Accuracy measures: Theoretical and practical concerns. International Makridakis, S. https://doi.org/10.1016/0169-2070(93)90079-3
  3. The Economics of Money, Banking, and Financial Markets Mishkin, F.S.
  4. Biometrika v.42 pp.523-526 A test for a change in a parameter occurring at an unknown point page, E.S. https://doi.org/10.1093/biomet/42.3-4.523
  5. Trading on the Edge pp.133-147 Genetic algorithms and financial applications Davis, L.;Deboeck, G.J. (Ed.)
  6. Technical Indicators Choi, J.
  7. Technical Analysis from A to Z Achelis, S.B.
  8. Genetic Algorithms in Search, Optimization, and Machine Learning Goldberg, D.E.
  9. Economerica v.28 pp.591-605 Tests of equality between sets of coefficients in two linear regressions Chow, G.C. https://doi.org/10.2307/1910133
  10. Journal of Forecasting v.1 pp.215-217 Evaluation of extrapolative forecasting methods: Results of academicians and practitioners Carbone, R.;Armstrong, J.S. https://doi.org/10.1002/for.3980010207
  11. Technometrics v.17 pp.61-64 Some one-sided tests for change in level Sen, A.K.;Srivastava, M.S. https://doi.org/10.2307/1268001
  12. Journal of American Statistical Association v.74 pp.365-367 On the likelihood ratio test for a shift in location of normal populations Worsley, K.J. https://doi.org/10.2307/2286336
  13. Proceedings of International Symposium of Forecasting pp.24 Can neural networks forecast in the big leagues? Comparing network forecasts to the pros? White, H.
  14. Sampling Techniques Cochran, W.G.
  15. Trading on the Edge pp.243-261 Hybrid neural, genetic, and fuzzy systems Wong, F.;Tan, C.;Deboeck, G.J. (Ed.)
  16. Intelligent Data Analysis v.3 pp.75-85 A piecewise regression analysis with automatic change-point detection Li, H.L.;Yu, J.R. https://doi.org/10.1016/S1088-467X(99)00006-2
  17. Machine Learning: Neural Networks, Genetic Algorithms, and Fuzzy Systems Adeli, H.;Hung, S.
  18. Applied Statistics v.28 no.2 pp.126-135 A non-parametric approach to the change-point problem Pettitt, A.N. https://doi.org/10.2307/2346729
  19. International Journal of Forecasting v.10 no.1 pp.1-4 Research respective on neural networks Gorr, W. https://doi.org/10.1016/0169-2070(94)90044-2
  20. Technical Indicators and Analysis Methods Chang, J.;Jung, Y.;Yeon, K.;Jun, J.;Shin, D.;Kim, H.
  21. Limit Theorems in Change-Point Analysis Csorgo, M.;Horvath, L.
  22. Econometrica v.59 pp.817-858 Heteroskedasticity and autocorrelation consistent covariance matrix estimation Andrews, D. https://doi.org/10.2307/2938229
  23. International Journal of Forecasting v.8 pp.69-80 Error measures for generalizing about forecasting methods: Empirical comparisons Armstrong, J.S.;Collopy, F. https://doi.org/10.1016/0169-2070(92)90008-W
  24. Annals of Mathematical Statistics v.35 pp.999-1018 Estimating the current mean of a normal distribution which is subjected to changes in time Chernoff, H.;Zacks, S. https://doi.org/10.1214/aoms/1177700517
  25. Intelligent Data Analysis v.1 pp.119-127 Possibilistic testing of distribution functions for change detection Wolkenhauer, O.;Edmunds, J.M. https://doi.org/10.1016/S1088-467X(97)00005-X
  26. Statistics and Probability Letters v.6 pp.181-189 Estimating the number of change-points via Schwarz's criterion Yao, Y.C. https://doi.org/10.1016/0167-7152(88)90118-6
  27. Nonparametric Methods in Change-point Problems Brodsky, B.E.;Darkhovsky, B.S.
  28. Investor's Guide to Technical Analysis: Predicting Price Action in the Markets Gifford, E.
  29. Modern Business Statistics Iman, R.;Conover, W.J.
  30. Annals of Mathematical Statistics v.37 pp.1196-1210 Test procedures for possible changes in parameters of statistical distributions occurring at unknown time points Kander, Z.;Zacks, S. https://doi.org/10.1214/aoms/1177699265
  31. Journal of American Statistical Association v.55 pp.324-330 Tests of the hypothesis that a linear regression system obeys two separate regimes Quandt, R.E. https://doi.org/10.2307/2281745
  32. Biometrika v.67 pp.79-84 A simple cumulative sum type statistic for the change-point problem with zero-one observations Pettitt, A.N. https://doi.org/10.1080/00949658008810413
  33. Journal of the American Statistical Associations v.66 pp.736-743 Inference in two-phase regression Hinkley, D.V. https://doi.org/10.2307/2284220
  34. Technical Analysis of Stock Trends Edwards, R.D.;Magee, J.
  35. Genetic algorithms and investment strategies Bauer, R.J.
  36. Expert Systems with Aplications v.19 no.2 pp.105-115 Using change-point detection to support artificial neural metworks for interest rates forecasting Oh, K.J.;Han, I. https://doi.org/10.1016/S0957-4174(00)00025-7
  37. IEEE Transactions on Neural Networks v.5 no.1 pp.39-53 Genetic evolution of the topology and weight distribution of neural networks Maniezzo, V. https://doi.org/10.1109/72.265959
  38. Journal of Applied Statistics v.4 pp.379-402 Comparison change analysis approach to change-point estimation Parzen, E.
  39. European Journal of Operational Research v.106 no.2-3 pp.570-584 Global optimization for artificial neural networks: A tabu search application Sexton, R.S.;Alidaee, B.;Dorsey, R.E.;Johnson, J.D. https://doi.org/10.1016/S0377-2217(97)00292-0
  40. Decision Support Systems v.22 no.2 pp.171-185 Toward global optimization of neural networks: A comparison of the genetic algorithm and backpropagation Sexton, R.S.;Dorsey, R.E.;Johnson, J.D. https://doi.org/10.1016/S0167-9236(97)00040-7
  41. Sequential Analysis: Tests and Confidence Intervals Siegmund, D.
  42. Journal of Business Economic Statistics v.10 pp.289-299 A direct test for changing trend Chu, C.S.J.;White, H. https://doi.org/10.2307/1391543
  43. Annals of Mathematical Statistics v.40 pp.116-126 On detecting changes in the mean of normal variates Gardner, L.A. Jr. https://doi.org/10.1214/aoms/1177697808
  44. Journal of Statistical Computation and Simulation v.11 pp.261-272 Some results on estimating a change-point using nonparametric type statistics Pettitt, A.N. https://doi.org/10.1093/biomet/67.1.79