Advertisement

Neural Computing and Applications

, Volume 31, Supplement 2, pp 1053–1074 | Cite as

Efficient financial time series prediction with evolutionary virtual data position exploration

  • Sarat Chandra NayakEmail author
  • Bijan Bihari Misra
  • Himansu Sekhar Behera
Original Article

Abstract

Prediction of stock index remains a challenging task of the financial time series prediction process. Random fluctuations in the stock index make it difficult to predict. Usually the time series prediction is based on the observations of past trend over a period of time. In general, the curve the time series data follows has a linear part and a non-linear part. Prediction of the linear part with past history is not a difficult task, but the prediction of non linear segments is difficult. Though different non-linear prediction models are in use, but their prediction accuracy does not improve beyond a certain level. It is observed that close enough data positions are more informative where as far away data positions mislead prediction of such non linear segments. Apart from the existing data positions, exploration of few more close enough data positions enhance the prediction accuracy of the non-linear segments significantly. In this study, an evolutionary virtual data position (EVDP) exploration method for financial time series is proposed. It uses multilayer perceptron and genetic algorithm to build this model. Performance of the proposed model is compared with three deterministic methods such as linear, Lagrange and Taylor interpolation as well as two stochastic methods such as Uniform and Gaussian method. Ten different stock indices from across the globe are used for this experiment and it is observed that in majority of the cases performance of the proposed EVDP exploration method is better. Some stylized facts exhibited by the financial time series are also documented.

Keywords

Virtual data position Financial time series Evolutionary computing Multilayer perceptron Deterministic interpolation Stochastic interpolation Genetic algorithm Stylized facts 

Notes

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. 1.
    Fama EF (1965) The behaviour of stock market prices. J Bus 38:34–105CrossRefGoogle Scholar
  2. 2.
    Fama EF (1970) Efficient capital markets: a review of theory and empirical work. J Financ 25:383–417CrossRefGoogle Scholar
  3. 3.
    Fama EF (1991) Efficient capital markets: II. J Financ 46(5):1575–1617CrossRefGoogle Scholar
  4. 4.
    Sexton RS, Gupta JND (2000) Comparative evaluation of genetic algorithm and back propagation for training neural networks. Inf Sci 129(1–4):45–59CrossRefzbMATHGoogle Scholar
  5. 5.
    Kuo RJ, Chen JA (2004) A decision support system for order selection in electronic commerce based on fuzzy neural network supported by real-coded genetic algorithm. Expert Syst Appl 26(2):141–154CrossRefGoogle Scholar
  6. 6.
    Chang P-C, Chen S-H, Lin K-L (2005) Two-phase sub population genetic algorithm for parallel machine-scheduling problem. Expert Syst Appl 29(3):705–712CrossRefGoogle Scholar
  7. 7.
    Nayak SC, Misra BB, Behera HS (2012) Index prediction using neuro-genetic hybrid networks: a comparative analysis of performance. In: Proceedings of the international conference on computing, communication, and applications (ICCCA), pp 1–6Google Scholar
  8. 8.
    Chen T (2009) A fuzzy-neural knowledge-based system for job completion time prediction and internal due date assignment in a wafer fabrication plant. Int J Syst Sci 40(8):889–902CrossRefzbMATHGoogle Scholar
  9. 9.
    Hsiao FH, Xu SD, Lin CY, Tsai ZR (2008) Robustness design of fuzzy control for Non-linear multiple time-delay large-scale systems via neural-network-based approach. IEEE Trans Syst Man Cybern Part BCybern 38(1):244–251CrossRefGoogle Scholar
  10. 10.
    Yixin Z, Shao F (2010) Stock data analysis based on BP neural network. In: Proceedings of second international conference on communication software and networks. IEEE Computer Society, Singapore, pp 396–399Google Scholar
  11. 11.
    Oliveira FA, Nobre C (2011) The use of artificial neural networks in the analysis and prediction of stock prices. In: Proceedings of IEEE international conference on systems, man, and cybernetics, Anchorage, Alaska, pp 2151–2155Google Scholar
  12. 12.
    Azadeh A, Ghaderi SF, Nokhandan BP, Nassiri S (2011) Improved one day-ahead price forecasting using combined time series and artificial neural network models for the electricity market. Int J Ind Syst Eng 9(3):249–267Google Scholar
  13. 13.
    Gadallah MH, Ali MB, Emam AM (2014) Particle swarm optimization: a triggered approach. Int J Ind Syst Eng 16(1):1–29Google Scholar
  14. 14.
    Khashei M, Hejazi SR, Bijari M (2008) A new hybrid artificial neural networks and fuzzy regression model for time series forecasting. Fuzzy Sets Syst 159(7):769–786MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Kazemi A, Sarrafha K, Beedel M (2014) A hybrid fuzzy decision making method for a portfolio selection: a case study of Tehran Stock Exchange. Int J Ind Syst Eng 18(3):335–354Google Scholar
  16. 16.
    Kabir G, Hasin MAA (2014) Application of adaptive neuro fuzzy inference system in demand forecasting for power engineering company. Int J Ind Syst Eng 18(2):237–255Google Scholar
  17. 17.
    Azadeh A, Eydi A, Raoofi Z, Rafiei H (2014) Optimization of net profit with uncertain inputs in manufacturing environments by integration of neural networks, genetic algorithm and fuzzy regression. Int J Ind Syst Eng 16(1):88–101Google Scholar
  18. 18.
    Atsalakis G, Valavanis K (2009) Surveying stock market forecasting techniques part II: soft computing methods. Expert Syst Appl 36(3, Part 2):5932–5941CrossRefGoogle Scholar
  19. 19.
    Goldberg DE (1989) Genetic algorithms in search optimization and machine learning. Pearson Education, LondonzbMATHGoogle Scholar
  20. 20.
    Storn R, Price K (1995) Differential evolution—a simple and efficient adaptive scheme for global optimization over continuous spaces. International Computer Science Institute, Berkeley, TR-95-012Google Scholar
  21. 21.
    Kennedy J, Eberhart RC, Shi Y (2001) Swarm intelligence. Morgan Kaufmann Publishers, San FranciscoGoogle Scholar
  22. 22.
    Nayak SC, Misra BB, Behera HS (2013) Hybridizing chemical reaction optimization and artificial neural network for stock future index forecasting. In: Proceedings of the 1st international conference on emerging trends and applications in computer science (ICETACS ‘13), pp 130–134Google Scholar
  23. 23.
    Nayak SC, Misra BB, Behera HS (2015) Artificial chemical reaction optimization of neural networks for efficient prediction of stock market indices. Ain Shams Eng J. doi: 10.1016/j.asej.2015.07.0 Google Scholar
  24. 24.
    Abdual-Salaml ME, Abdul-Kader, Abdel-Wahed WF (2010) Comparative study between differential evolution and particle swarm optimization algorithms in training of feed-forward neural network for stock price prediction. In: The 7th international conference on informatics and systems, Cairo, pp 1–8Google Scholar
  25. 25.
    Huang H, Pasquier M, Quek C (2009) Financial market trading system with a hierarchical coevolutionary fuzzy predictive model. IEEE Trans Evol Comput 13(1):56–70CrossRefGoogle Scholar
  26. 26.
    Kwon YK, Moon BR (2007) A hybrid neuro genetic approach for stock forecasting. IEEE Trans Neural Netw 18(3):851–864CrossRefGoogle Scholar
  27. 27.
    Lee Y, Tong L (2011) Forecasting time series using a methodology based on autoregressive integrated moving average and genetic programming. Knowl Based Syst 24(1):66–72CrossRefGoogle Scholar
  28. 28.
    Hadavandi E, Shavandi H, Ghanbari A (2010) Integration of genetic fuzzy systems and artificial neural networks for stock price forecasting. Knowl Based Syst 23(8):800–808CrossRefGoogle Scholar
  29. 29.
    Hadavandi E, Ghanbari A, Naghneh S (2010) Developing a time series model based on particle swarm optimization for gold price forecasting. In: Third international conference on business intelligence and financial engineering, pp 337–340Google Scholar
  30. 30.
    Yu L, Zhang YQ (2005) Evolutionary fuzzy neural networks for hybrid financial prediction. IEEE Trans Syst Man Cybern Part C Appl Rev 35(2):244–249CrossRefGoogle Scholar
  31. 31.
    Khashei M, Bijari M (2011) A novel hybridization of artificial neural networks and ARIMA model for time series forecasting. Appl Soft Comput 11(2):2664–2675CrossRefGoogle Scholar
  32. 32.
    Khashei M, Bijari M (2012) A new class of hybrid models for time series forecasting. Expert Syst Appl 39(4):4344–4357CrossRefGoogle Scholar
  33. 33.
    Manimaran P, Selladurai V, Ranganathan R, Sasikumar G (2011) Genetic Algorithm for optimisation of distribution system in a single stage supply chain network with fixed charges. Int J Ind Syst Eng 7(3):292–316Google Scholar
  34. 34.
    Cont R (2001) Empirical properties of asset returns: stylized facts and statistical issues. Quant Financ 1:223–236CrossRefzbMATHGoogle Scholar
  35. 35.
    Danielsson J (2011) Financial risk forecasting. Wiley, HobokenGoogle Scholar
  36. 36.
    Sewell M (2011) Characterization of financial time series. UCL Department of Computer Science, Research NoteGoogle Scholar
  37. 37.
    Taylor S (2007) Asset price dynamics, volatility, and prediction. Princeton University Press, PrincetonzbMATHGoogle Scholar
  38. 38.
    Franses P, van Dijk D (2000) Non-linear time series models in empirical finance. Cambridge University Press, CambridgeCrossRefGoogle Scholar
  39. 39.
    Cybenko G (1989) Approximation by superposition of a sigmoidal functions. Math Control Signals Syst 2:303–314MathSciNetCrossRefzbMATHGoogle Scholar
  40. 40.
    Haykin S (2003) Neural networks: a comprehensive foundation. Prentice Hall, New JerseyzbMATHGoogle Scholar
  41. 41.
    Nayak SC, Misra BB, Behera HS (2014) Impact of data normalization on stock index forecasting. Int J Comput Inf Syst Ind Manag 6:357–369Google Scholar
  42. 42.
    Nayak SC, Misra BB, Behera HS (2012) Evaluation of normalization methods on neuro-genetic models for stock index forecasting. In: IEEE world congress on information and communication technologies (WICT 2012). doi: 10.1109/WICT.2012.6409147
  43. 43.
    Jo T (2013) VTG schemes for using back propagation for multivariate time series prediction. Appl Soft Comput 13(5):2692–2702CrossRefGoogle Scholar
  44. 44.
    Nayak SC, Misra BB, Behera HS (2017) Exploration and incorporation of virtual data positions for efficient forecasting of financial time series. Int J Ind Syst Eng 26(1):42–62Google Scholar
  45. 45.
    Jo T (2004) The effect of deterministic and stochastic VTG schemes on the application of backpropagation to multivariate time series prediction. In: International conference on industrial, engineering and other applications of applied intelligent systems. Springer, Berlin, pp 107–117Google Scholar
  46. 46.
    Small G, Wong R (2002) The validity of forecasting. A Paper for Presentation at the Pacific Rim Real Estate Society International Conference, Christchurch, New Zealand, pp 1–14Google Scholar
  47. 47.
    Makridakis S, Wheelwright SC, Hyndman RJ (2008) Forecasting methods and applications. Wiley, HobokenGoogle Scholar
  48. 48.
    Theil H (1971) Applied economic forecasting. North-Holland Publishing Company, AmsterdamGoogle Scholar
  49. 49.
    Makridakis S, Andersen A, Carbone R, Fildes R, Hibon M, Lewandowski R, Winkler R (1982) The accuracy of extrapolation (time series) methods: results of a forecasting competition. J Forecast 1(2):111–153CrossRefGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2017

Authors and Affiliations

  • Sarat Chandra Nayak
    • 1
    Email author
  • Bijan Bihari Misra
    • 2
  • Himansu Sekhar Behera
    • 3
  1. 1.Department of Computer Science and EngineeringKommuri Pratap Reddy Institute of TechnologyHyderabadIndia
  2. 2.Department of Information TechnologySilicon Institute of TechnologyBhubaneswarIndia
  3. 3.Department of Computer Science Engineering and Information TechnologyVeer Surendra Sai University of TechnologyBurlaIndia

Personalised recommendations