NXCS: Hybrid Approach to Stock Indexes Forecasting



In this chapter, a hybrid approach for stock market forecasting is presented. It allows to develop a mixture of hybrid experts, each consisting of a genetic classifier and an associated artificial neural network. The resulting experts have been applied to stock market forecasting using technical trading rules as genetic inputs and other inputs—in particular past quotations—for the neural networks. In particular, the former are used to find quasi-stationary regimes within the financial data series, whereas the latter are assigned the task of making “context-dependent” predictions on the next day trend of the market. To this end, a novel kind of feedforward artificial neural network has been defined, allowing to implement suitable predictors without being compelled to exploit more complex neural architectures. Test runs have been performed on some well-known stock market indexes, also taking into account trading commissions. The tests pointed to the good forecasting capability of the proposed approach, which repeatedly outperformed the buy-and-hold strategy.


Stock Market Forecasting Time Series Prediction Genetic Algorithms eXtended Classifier Systems (XCSs) Artificial Neural Networks 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Achelis, S. B. (1995). Technical Analysis from A to Z, 2nd ed. Chicago: Irwin Professional PublishingGoogle Scholar
  2. Bengio Y. and F. Gingras (1998). “Handling Asynchronous or Missing Data with Recurrent Networks,” International Journal of Computational Intelligence and Organizations, 1(3), 154–163.Google Scholar
  3. Breiman, L., J. Friedman, R. Olshen, and C. Stone (1984). Classification and Regression Trees. Belmont, CA: Wadsworth International Group.Google Scholar
  4. Campbell, J. Y., A. W. Lo, and A. C. MacKinlay (1997). The Econometrics of Financial Markets. Princeton, New Jersey: Princeton University Press.Google Scholar
  5. Campolucci, P., A. Uncini, F. Piazza, and B. D. Rao (1999). “On-Line Learning Algorithms for Locally Recurrent Neural Networks,” IEEE Transactions on Neural Networks, 10(2), 253–271.CrossRefGoogle Scholar
  6. Castiglione, F. (2001). “Forecasting Price Increments Using an Artificial Neural Network,” Advances in Complex Systems, 4(1), 45–56.CrossRefGoogle Scholar
  7. Clark, P. and T. Niblett (1989). “The CN2 Induction Algorithm,” Machine Learning Journal, 3(4), 261–283.Google Scholar
  8. Cover T. M. and P. E. Hart (1967). “Nearest Neighbor Pattern Classification,” IEEE Transactions on Information Theory, 13(1), 21–27.CrossRefGoogle Scholar
  9. Deboeck G. (1993). “Neural, Genetic, and Fuzzy Approaches to Design of Trading Systems,” Proceedings of the 2nd Annual International Conference on AI Applications on Wall Street: Tactical and Strategic Computing Technologies, 184–193.Google Scholar
  10. Fahlmann S. E. and C. Lebiere (1990). The Cascade-Correlation Learning Architecture, Technical Report CMU-CS-90-100, Carnegie Mellon University.Google Scholar
  11. Fama E. F. (1965). “The Behavior of Stock Market Prices,” The Journal of Business, 38, 34–105.CrossRefGoogle Scholar
  12. Friedman, J. H. (1991). “Multivariate Adaptive Regression Splines,” Annals of Statistics, 19(1), 1–141.CrossRefGoogle Scholar
  13. Friedman J. H., F. Baskett, and L. J. Shustek (1975). “An Algorithm for Finding Nearest Neighbors,” IEEE Transactions On Computers, 24(10), 1000–1006.CrossRefGoogle Scholar
  14. Giles, C. L., S. Lawrence, and A. Chung Tsoi (1997). “Rule Inference for Financial Prediction using Recurrent Neural Networks,” Proceedings of IEEE/IAFE Conference on Computational Intelligence for Financial Engineering (CIFE), 253–259.Google Scholar
  15. Goldberg, D. E. (1989). Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley.Google Scholar
  16. Hamilton, J. D. (1994). Time series analysis. Princeton University Press.Google Scholar
  17. Hardie, W., H. Lutkepohl, and R. Chen (1997). “A Review of Non-parametric Time Series Analysis,” International Statistical Review, 65, 49–72.CrossRefGoogle Scholar
  18. Hawawini, G. and D. B. Keim (1995). “On the Predictability of Common Stock Returns: World-wide Evidence,” in R.A. Jarrow, V. Maksimovic and W.T. Ziemba (eds.), Handbook in Operations Research and Management Science, 9, 497–544. Amsterdam: North-Holland.Google Scholar
  19. Hellström, T. and K. Holmström (1997). Predicting the Stock Market, Technical Report IMa-TOM-1997-07. Department of Mathematics and Physics, Malardalen University, Sweden.Google Scholar
  20. Holland, J. H. (1976). “Adaptation,” in R. Rosen and F. M. Snell (eds.), Progress in Theoretical Biology, 4, 263–293. New York: Academic Press.Google Scholar
  21. Holland, J. H. (1986). “Escaping Brittleness: The possibilities of General-Purpose Learning Algorithms Applied to Parallel Rule-Based Systems,” in R.S. Michalski, J. Carbonell, and M. Mitchell (eds.), Machine Learning II, 593–623. Morgan Kaufmann.Google Scholar
  22. Jacobs, R. A., M. I. Jordan, S. J. Nowlan, and G. E. Hinton (1991). “Adaptive Mixtures of Local Experts,” Neural Computation, 3, 79–87.CrossRefGoogle Scholar
  23. Jordan, M. I. and R. A. Jacobs (1992). “Hierarchies of Adaptive Experts,” in J. Moody, S. Hanson, and R. Lippman (eds.), Advances in Neural Information Processing Systems, 4, 985–993. Morgan Kaufmann.Google Scholar
  24. Jordan, M. I. and R. A. Jacobs (1994). “Hierarchical Mixtures of Experts and the EM Algorithm,” Neural Computation, 6, 181–214.CrossRefGoogle Scholar
  25. Fu, K. and W. Xu (1997). “Training Neural Network with Genetic Algorithms for Forecasting the Stock Price Index,” Proceedings of the 1997 IEEE International Conference on Intelligent Processing Systems, 1, 401–403.Google Scholar
  26. Kantz, H. and T. Schreiber (1997). Nonlinear Time Series Analysis, Cambridge Nonlinear Science Series 7. Cambridge University Press.Google Scholar
  27. Kovacs, T. (1996). Evolving Optimal Populations with XCS classifier Systems, MSc. Dissertation. University of Birmingham, UK.Google Scholar
  28. Kovacs, T. (1999). “Strength or Accuracy? A Comparison of Two Approaches to Fitness,” A. S. Wu (ed.), Second International Workshop on Learning Classifier Systems during GECCO99, 258–265.Google Scholar
  29. Lanzi, P. L. (1997). “A study of the Generalization Capabilities of XCS,” Proceedings of the Seventh International Conference on Genetic Algorithms (ICGA97), 418–425. San Francisco, CA: Morgan Kaufmann.Google Scholar
  30. Lanzi, P. L. (1998). “Adding Memory to XCS,” Proceedings of the IEEE Conference on Evolutionary Computation (ICEC98), 609–614.Google Scholar
  31. Lanzi, P. L. and A. Perrucci (1999). “Extending the Representation of Classifier Conditions Part II: From Messy Coding to S-Expressions,” Proceedings of the Genetic and Evolutionary Computation Conference (GECCO ′99), 1, 345–353. Morgan Kaufmann.Google Scholar
  32. LeBaron, B. (1991). Technical Trading Rules and Regime Shifts in Foreign Exchange, Technical Report. Department of Economics, University of Wisconsin, Madison, WI.Google Scholar
  33. LeBaron, B. and A. S. Weigend (1997). “A Boostrap Evaluation of the Effect of Data Splitting on Financial Time Series,” IEEE Transactions on Neural Networks, 9, 213–220.Google Scholar
  34. Lewis, P. A. W., B. K. Ray, and J. G. Stevens (1994). “Modelling Time Series Using Multivariate Adaptive Regression Splines,” in A. S. Weigend and N. A. Gershenfeld (eds.), Time Series Prediction: Forecasting the Future and Understanding the Past, 296–318. Addison Wesley.Google Scholar
  35. Mahfoud, S. and G. Mani (1996). “Financial Forecasting Using Genetic Algorithms,” Applied Artificial Intelligence, 10(6), 543–565.CrossRefGoogle Scholar
  36. McCullagh, P. and J. A. Neider (1989). Generalized Linear Models. London: Chapman and Hall.Google Scholar
  37. Muhammad, A. and G. A. King (1997). “Foreign Exchange Market Forecasting Using Evolutionary Fuzzy Networks,” Proceedings of the IEEE /IAFE 1997 Computational Intelligence for Financial Engineering, 213–219.Google Scholar
  38. Nelson, D. B. (1991). “Conditional Heteroskedasticity in Asset Returns: A New Approach,” Econometrica, 59, 347–370.CrossRefGoogle Scholar
  39. Noever, D. and S. Baskaran (1994). “Genetic algorithms trading on the S&P500,” The Magazine of Articial Intelligence in Finance, 1(3), 41–50.Google Scholar
  40. Quinlan, J. R. (1986). “Induction of Decision Trees,” Machine Learning, 1, 81–106.Google Scholar
  41. Quinlan, J. R. (1993). Programs for Machine Learning. Los Altos, CA: Morgan Kaufmann.Google Scholar
  42. Refenes, A. P. N., A. N. Burgess, and Y. Bentz (1997). “Neural Networks in Financial Engineering: A Study in Methodology”, IEEE Transactions on Neural Networks, 8(6), 1222–1267.CrossRefGoogle Scholar
  43. Refenes, A. P. N., A. Zapranis, and G. Francis (1997). “Stock performance modeling using neural networks: A Comparative Study with Regression Models,” Neural Networks, 7(2), 375–388. Elsevier.CrossRefGoogle Scholar
  44. Rumelhart, D. E. and J. L. McLelland (1986). Parallel Distributed Processing, Explorations in the Microstructure of Cognition, 1, Foundations, MIT Press.Google Scholar
  45. Salmon, M. (2000). “Measuring Dependency in Non-Gaussian Financial Assets,” Fifth International Meeting on Quantitative Methods in Applied Sciences.Google Scholar
  46. Sun, R. and T. Peterson (1999). “Multi-Agent Reinforcement Learning: Weighting and Partitioning,” Neural Networks, 12(4-5), 727–753.CrossRefGoogle Scholar
  47. Sutton, R. S. and A. G. Barto (1998). Reinforcement Learning: An Introduction. Cambridge, MA: MIT Press.Google Scholar
  48. Tong, H. and K. S. Lim (1980). “Threshold Autoregression, Limit Cycles and Cyclical Data,” Journal of Royal Statistics Society, 42, 245–292.Google Scholar
  49. Tsay, R. (1989). “Testing and Modeling Threshold Autoregressive Processes,” Journal of the American Statistical Association, 84, 431–452.CrossRefGoogle Scholar
  50. Weigend, A. S. (1996). “Time Series Analysis and Prediction Using Gated Experts with Application to Energy Demand Forecast,” Applied Artificial Intelligence, 10, 583–624.CrossRefGoogle Scholar
  51. Weigend, A. S. and H. G. Zimmermann (1998). “Exploiting Local Relations as Soft Constraints to Improve Forecasting,” Journal of Computational Intelligence in Finance, 6, 14–23.Google Scholar
  52. Weigend, A. S., M. Mangeas, and A. N. Srivastava (1995). “Nonlinear Gated Experts for Time Series: Discovering Regimes and Avoiding Overfitting,” International Journal of Neural Systems, 6, 373–399.CrossRefGoogle Scholar
  53. Wilson, S. W. (1995). “Classifier Fitness Based on Accuracy,” Evolutionary Computation, 3(2), 149–175.CrossRefGoogle Scholar
  54. Wilson, S. W. (1998). “Generalization in the XCS classifier System,” Proceedings of the Third annual Genetic Programming Conference, 665–674. San Francisco, CA: Morgan Kaufmann.Google Scholar
  55. Wilson, S. W. (1999). “Get Real! XCS with Continuous-Valued Inputs,” in L. Booker, S. Forrest, M. Mitchell, and R. Riolo (eds.), Festschrift in Honor of John H. Holand, 111–121. Center of Study of Complex Systems, The University of Michigan, ANN Arbor, MI.Google Scholar

Copyright information

© Springer Science+Business Media New York 2002

Authors and Affiliations

  1. 1.DIEE, University of CagliariCagliariItaly

Personalised recommendations