Skip to main content

Stock market prediction with multiple classifiers


Stock market prediction is attractive and challenging. According to the efficient market hypothesis, stock prices should follow a random walk pattern and thus should not be predictable with more than about 50 percent accuracy. In this paper, we investigated the predictability of the Dow Jones Industrial Average index to show that not all periods are equally random. We used the Hurst exponent to select a period with great predictability. Parameters for generating training patterns were determined heuristically by auto-mutual information and false nearest neighbor methods. Some inductive machine-learning classifiers—artificial neural network, decision tree, and k-nearest neighbor were then trained with these generated patterns. Through appropriate collaboration of these models, we achieved prediction accuracy up to 65 percent.

This is a preview of subscription content, access via your institution.


  1. 1.

    Fama EF, Fisher L, Jensen M, Roll R (1969) The adjustment of stock price to new information. Int Eco Rev 10(1):1–21

    Article  Google Scholar 

  2. 2.

    Fama EF (1991) Efficient capital markets: II J Fin 46(5):1575–1617

    Article  Google Scholar 

  3. 3.

    Cootner PH (1964) The random character of stock market prices. MIT Press, MA

    Google Scholar 

  4. 4.

    Fama EF (1965) The behaviour of stock market prices. J Bus 38:34–105

    Article  Google Scholar 

  5. 5.

    Alexander SS (1961) Price movements in speculative markets: Trends or random walks. Ind Manage Rev pp 7–26

  6. 6.

    Jensen MC (1978) Some anomalous evidence regarding market efficiency. J Fin Eco 6:95–102

    Article  Google Scholar 

  7. 7.

    Gallagher L, Taylor M (2002) Permanent and temporary components of stock prices: Evidence from assessing macroeconomic stocks. Southern Eco J 69:245–262

    Google Scholar 

  8. 8.

    Lo AW, MacKinlay AC (1997) Stock market prices do not follow random walks. Market Efficiency: Stock Market Behaviour in Theory and Practice 1:363–389

    Google Scholar 

  9. 9.

    Kavussanos MG, Dockery E (2001) A multivariate test for stock market efficiency: The case of ASE Applied Financial Economics 11(5):573–579(7)

    Google Scholar 

  10. 10.

    Kirt CB, Malaikah SJ (1992) Efficiency and inefficiency in thinly traded stock markets: Kuwait and Saudi Arabia. J Bank & Fin 16(1):197–210

    Article  Google Scholar 

  11. 11.

    Walczak S (2001) An empirical analysis of data requirements for financial forecasting with neural networks. J Manag Infor Syst 17(4):203–222

    MathSciNet  Google Scholar 

  12. 12.

    Baestaens DJE, van den Bergh WM, Vaudrey H (1996) Market inefficiencies, technical trading and neural networks. In: Dunis C (ed) forecasting financial markets, financial economics and quantitative analysis. John Wiley & Sons, Chichester, England, pp 254– 260

    Google Scholar 

  13. 13.

    Tsibouris G, Zeidenberg M (1995) Testing the efficient markets hypothesis with gradient descent algorithms. In: Refenes AP (ed) Neural networks in the capital markets. John Wiley & Sons, Chichester, England, Chap 8, pp 127–136

  14. 14.

    Hellstrom T, Holmstrom K (1998) Predicting the stock market, technical report series IMa-TOM-1997-07, Center of Mathematical Modeling, Malardalen University

  15. 15.

    Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Net 2(5):259–366

    Google Scholar 

  16. 16.

    Refenes A (1995) Neural networks in the capital markets. Wiley, New York

    Google Scholar 

  17. 17.

    Gately E (1996) Neural networks for financial forecasting. Wiley, New York

    Google Scholar 

  18. 18.

    Zirilli JS (1997) Financial prediction using neural networks. International Thomson Computer Press, UK

    Google Scholar 

  19. 19.

    White H (2000) A reality check for data snooping. Econometrica 68(5):1097–1126

    Article  MathSciNet  Google Scholar 

  20. 20.

    Hurst HE (1951) Long-term storage of reservoirs: an experimental study. Trans Amer Soc Civil Engi 116:770–799

    Google Scholar 

  21. 21.

    Mandelbrot BB, Ness JV (1968) Fractional brownian motions, fractional noises and applications. SIAM Rev 10:422–437

    Article  MathSciNet  Google Scholar 

  22. 22.

    Mandelbrot B (1982) The fractal geometry of nature. WH Freeman, New York

    MATH  Google Scholar 

  23. 23.

    May CT (1999) Nonlinear pricing: theory & applications. Wiley, New York

    Google Scholar 

  24. 24.

    Corazza M, Malliaris AG (2002) Multi-fractality in foreign currency markets. Multinat Fin J 6(2):65–98

    Google Scholar 

  25. 25.

    Grech D, Mazur Z (2004) Can one make any crash prediction in finance using the local Hurst exponent idea?. Physica A: Statistical Mech Appl 336:133–145

    Article  Google Scholar 

  26. 26.

    Peters EE (1991) Chaos and order in the capital markets: a new view of cycles, prices, and market volatility. Wiley, New York

    Google Scholar 

  27. 27.

    Peters EE (1994) Fractal market analysis: applying chaos theory to investment and economics. Wiley, New York

    Google Scholar 

  28. 28.

    Qian B, Rasheed K (2004) Hurst exponent and financial market predictability. In: Proceedings of The 2nd IASTED international conference on financial engineering and applications. Cambridge, MA, USA, pp 203–209

  29. 29.

    Walczak S (2001) An empirical analysis of data requirements for financial forecasting with neural networks. J Manag Infor Syst 17(4):203–222

    MathSciNet  Google Scholar 

  30. 30.

    Hsieh DA (1991) Chaos and nonlinear dynamics: application to financial markets. J Fin 46:1839–1877

    Article  Google Scholar 

  31. 31.

    Takens F (1981) Dynamical system and turbulence. In: Rand A, Young Ls (eds) Lecture notes in mathematics, 898(Warwick 1980). Springer, Berlin

  32. 32.

    Cao L (1997) Practical method for determining the minimum embedding dimension of a scalar time series. Physica D 110:43–50

    Article  Google Scholar 

  33. 33.

    Soofi AS, Cao L (2002) Modelling and forecasting financial data: techniques of nonlinear dynamics. Kluwer Academic Publishers: Norwell, Massachusetts

    Google Scholar 

  34. 34.

    Frank RJ, Davey N, Hunt SP (2000) Input window size and neural network predictors. IEEE-INNS-ENNS Int Joint Conf Neural Netw (IJCNN’00)-Vol 2, pp. 2237–2242

  35. 35.

    Merkwirth C, Parlitz U, Wedekind I, Lauterborn W (2002) TSTOOL user manual,

  36. 36.

    Hagan MT, Demuth HB, Beale MH (1996) Neural network design. PWS Publishing, Boston, MA

    Google Scholar 

  37. 37.

    Hagan MT, Menhaj M (1994) Training feedforward networks with the Marquardt algorithm. IEEE Trans Neural Netw 5(6):989–993

    Article  Google Scholar 

  38. 38.

    Aha D, Kibler DW, Albert MK (1991) Instance-based learning algorithms. Mach Learn 6:37–66

    Google Scholar 

  39. 39.

    Mitchell T (1997) Decision tree learning, machine learning. The McGraw-Hill Companies, Inc., pp 52–78

  40. 40.

    Breiman L, Friedman J, Stone CJ, Olshen RA (1984) Classification and regression trees. Chapman & Hall (Wadsworth, Inc.), New York

    MATH  Google Scholar 

  41. 41.

    Stone M (1974) Cross-validatory choice and assessment of statistical prediction. J Roy Statistic Soc B 36:111–120

    Google Scholar 

  42. 42.

    Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140

    MathSciNet  Google Scholar 

  43. 43.

    Dietterich TG (1997) Machine-learning research: Four current direction. AI Magazine 18(4):97–136

    Google Scholar 

  44. 44.

    Hansen L, Salamon P (1990) Neural network ensembles. IEEE Trans Patt Analy Mach Intell (12):993–1001

  45. 45.

    Dietterich TG (2000) Ensemble methods in machine learning. First International Workshop on Multiple Classifier Systems, New York

  46. 46.

    Schapire RE, Freund Y, Bartlett P, Lee WS (1997) Boosting the margin: A new explanation for the effectiveness of voting methods. In: Proceedings of the fourteenth international conference on machine learning. Morgan Kaufmann, pp 322–330

  47. 47.

    Wolpert DH (1992) ‘Stacked generalization,’ Neural networks. Pergamon Press, vol 5, pp. 241–259

  48. 48.

    Ting KM, Witten IH (1999) Issues in stacked generalization. J Artif Intell Res 10:271–289

    Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Bo Qian.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Qian, B., Rasheed, K. Stock market prediction with multiple classifiers. Appl Intell 26, 25–33 (2007).

Download citation


  • Stock market prediction
  • Efficient market hypothesis
  • Hurst exponent
  • Machine learning
  • Model ensemble