Automatic optimized support vector regression for financial data prediction

Abstract

The aim of this article is to introduce a hybrid approach, namely optimal multiple kernel–support vector regression (OMK–SVR) for time series data prediction and to analyze and compare its performances against those of support vector regression with a single RBF kernel (RBF-SVR), gene expression programming (GEP) and extreme learning machine (ELM) on the financial series formed by the monthly and weekly values of Bursa Malaysia KLCI Index, monthly values of Dow Jones Industrial Average Index (DJIA) and New York Stock Exchange. Our method provides an optimal multiple kernel and optimal parameters in Support Vector Regression, improving the accuracy of prediction. The proposed approach is structured on two levels. The macro-level uses a breeder genetic algorithm for choosing the optimal multiple kernel and the SVR optimal parameters. The fitness function of each chromosome is computed in the micro-level using a SVR algorithm. The regression model based on the optimal multiple kernel and optimal parameters is then validated and used for forecasting. The experimental results prove that OMK–SVR performs better than GEP, RBF-SVR and ELM for predicting the future behavior of the study series. A sensitivity study with respect to the number of kernels from the multiple kernel used by OMK–SVR and with respect to the ratio between training and testing data sets was conducted.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

References

  1. 1.

    Makridakis S, Wheelwright SC, Hyndman RJ (1998) Forecasting methods and applications. Wiley, New York

    Google Scholar 

  2. 2.

    Zhang G, Patuwo BE, Hu MY (1998) Forecasting with artificial neural networks: the state of the art. Int J Forecast 14(1):35–62

    Article  Google Scholar 

  3. 3.

    Smola AJ, Scholkopf B (2004) A tutorial on support vector regression. Stat Comput 14:199–222

    MathSciNet  Article  Google Scholar 

  4. 4.

    Drucker H, Burges CJC, Kaufman L, Smola A, Vapnik V (1997) Support vector regression machines. Neural Inf Proc Syst 9:155–161

    Google Scholar 

  5. 5.

    Kang F, Xu Q, Li J (2016) Slope reliability analysis using surrogate models via new support vector machines with swarm intelligence. Appl Math Model 40(11–12):6105–6120

    MathSciNet  Article  MATH  Google Scholar 

  6. 6.

    Li Q, Jiang S (2004) Gene expression programming in prediction. In: WCICA 2004. Fifth world congress on control and automation. https://doi.org/10.1109/wcica.2004.1341971

  7. 7.

    Huang G-B, Zhu Q-Y, Siew C-K (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501

    Article  Google Scholar 

  8. 8.

    Kang F, Liu J, Li J, Li S (2017) Concrete dam deformation prediction model for health monitoring based on extreme learning machine. Struct Control Health 24(10):e1997

    Article  Google Scholar 

  9. 9.

    Majhi R, Panda G, Sohoo S, Panda A, Choubey A (2008) Prediction of S&P 500 and DJIA stock indices using particle swarm optimization technique. In: Proc IEEE congress on evolutionary computation, pp 1276–1282

  10. 10.

    Mehak U, Kamran R, Syed HA, Syed SAA (2016) Stock market prediction using machine techniques. In: Proceedings of the 3rd international conference on communications and information sciences. https://doi.org/10.1109/iccoins.2016.7783235

  11. 11.

    Allen DE, McAller M, Singh AK (2014) Machine nees and volatility: the don jones industrial average and the TRNA sentiment series. E-Prints Complutense. http://eprints.ucm.es/24356/. Accessed 1 July 2017

  12. 12.

    Bărbulescu A, Băutu E (2012) A Hybrid Approach for Modeling Financial Time Series. Int Arab J Inf Techn 9(4):327–335

    Google Scholar 

  13. 13.

    Yao J, Poh H-L (1995) Forecasting the KLSE index using neural networks. In: Proceedings of ICNN’95, pp 1012–1017. https://doi.org/10.1109/icnn.1995.487559

  14. 14.

    Chen W-H, Shih J-Y (2006) Comparison of support-vector machines and back propagation neural networks in forecasting the six major Asian stock markets. Int J Electron Fin 1(1):49–67

    Article  Google Scholar 

  15. 15.

    Chandwani D, Saluja MS (2014) Stock direction forecasting techniques: an empirical study combining machine learning system with market indicators in the indian context. Int J Comput Appl 92(11):8–17

    Google Scholar 

  16. 16.

    Choudhry R, Garg K (2008) A Hybrid machine learning system for stock market forecasting. Eng Technol 2(3):689–692

    Google Scholar 

  17. 17.

    Shazly MRE, Shazly HEE (1999) Forecasting currency prices using genetically evolved neural network architecture. Int Rev Financ Anal 8(1):67–82

    Article  Google Scholar 

  18. 18.

    Gestel TV et al (2001) Financial time-series prediction using least squares support vector machines within the evidence framework. IEEE T Neural Netw 12(4):809–821

    Article  Google Scholar 

  19. 19.

    Tarsauliya A et al (2010) Analysis of Artificial Neural Network for Financial Time Series Forecasting. Int J Comput Appl 9(5):16–22

    Google Scholar 

  20. 20.

    Mizuno H, Kosaka M, Yajima H (1998) Application of neural network to technical analysis of stock market prediction. Stud Inf Control 7(2):111–120

    Google Scholar 

  21. 21.

    Wunsch DC, Saad EW, Prokhorov DV (1998) Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks. IEEE T Neural Netw 9(6):1456–1460

    Article  Google Scholar 

  22. 22.

    Khandelwal I, Adhikari R, Verma G (2015) Time series forecasting using hybrid ARIMA and ANN models based on DWT decomposition. Proc Comput Sci 48:173–179

    Article  Google Scholar 

  23. 23.

    Merh N, Saxena VP, Pardasani KR (2010) A comparison between hybrid approaches of ANN and ARIMA for Indian stock trend forecasting. Bus Intel J 3(2):23–43

    Google Scholar 

  24. 24.

    Yao X, Liu Y (1997) A new evolutionary system for evolving artificial neural networks. IEEE T Neural Netw 8(3):694–713

    Article  Google Scholar 

  25. 25.

    Mayer HA, Schwaiger R (1999) Evolutionary and coevolutionary approaches to time series prediction using generalized multi-layer perceptrons. In: Proceedings of 1999 congress on evolutionary computation—CEC99, vol 1, pp 275–280. https://doi.org/10.1109/cec.1999.781936

  26. 26.

    Flores J et al (2009) Financial time series forecasting using a hybrid neural-evolutive approach. In: Proceedings of 15th SIGEF international conferecne, Lugo, Spain, pp 547–555

  27. 27.

    Kim KJ (2003) Financial time series forecasting using support vector machines. Neurocomputing 55(1–2):307–319

    Article  Google Scholar 

  28. 28.

    Cao L, Tay FEH (2001) Financial forecasting using support vector machines. Neural Comput Appl 10:184–192

    Article  MATH  Google Scholar 

  29. 29.

    Cao L (2003) Support vector machines experts for time series forecasting. Neurocomputing 51:321–339

    Article  Google Scholar 

  30. 30.

    de Oliveira JFL, Ludermir TB (2014) Iterative ARIMA-Multiple Support Vector Regression models for long term time series prediction. In: ESANN 2014 proceedings, European symposium on artificial neural networks, computational intelligence and machine learning. Bruges, Belgium http://www.i6doc.com/fr/livre/?GCOI=28001100432440

  31. 31.

    Vapnik V (1995) The nature of statistical learning theory. Springer, Berlin

    Google Scholar 

  32. 32.

    Basak D, Pal S, Patranabis DC (2007) Support vector regression. Neu Inf Pro Lett Rev 11(10):203–224

    Google Scholar 

  33. 33.

    Huang Q, Mao J, Liu Y (2012) An improved grid search algorithm of SVR parameters optimization. In: 2012 IEEE 14th international conference on communication technology. https://doi.org/10.1109/icct.2012.6511415

  34. 34.

    Diosan L, Oltean M, Rogozan A, Pecuchet JP (2007) Improving SVM performance using a linear combination of kernels. In Proceedings of the ICANNGA07, LNCS, vol 4432, pp 218–227

  35. 35.

    Simian D, Stoica F (2012) A general frame for building optimal multiple SVM kernels. LNCS 7116:256–263

    Google Scholar 

  36. 36.

    Gonen M, Alpaydın E (2011) Multiple kernel learning algorithms. J Mach Learn Res 12:2211–2268

    MathSciNet  MATH  Google Scholar 

  37. 37.

    Minh HQ, Niyogi P, Yao Y (2006) Mercers theorem feature maps, and smoothing learning theory. Lect Notes Comput Sci 4005:154–168

    Article  MATH  Google Scholar 

  38. 38.

    Stoica F, Cacovean LF (2009) Using genetic algorithms and simulation as decision support in marketing strategies and long-term production planning. In: Proceedings of 9th international conference on simulation, modelling and optimization (SMO ‘09), pp 435–439

  39. 39.

    Mühlenbein H, Schlierkamp-Voosen D (1994) Predictive models for the breeder genetic algorithm. I Continuous parameter optimization. Evol Comput 1(1):25–49

    Article  Google Scholar 

  40. 40.

    Stoica F, Gh Boitor C (2014) Using the Breeder genetic algorithm to optimize a multiple regression analysis model used in prediction of the mesiodistal width of unerupted teeth. Int J Comput Commun 9(1):62–70

    Article  Google Scholar 

  41. 41.

    Chang C-C, Lin C-J (2001) LIBSVM: a library for support vector machines. http://www.csie.ntu.edu.tw/~cjlin/libsvm

  42. 42.

    Bautu E, Barbulescu A (2013) Forecasting meteorological time series using soft computing methods: an empirical study. Appl Math Inf Sci 7(4):1297–1306

    Article  Google Scholar 

  43. 43.

    Crone SF, Lessmann S, Pietsch S (2006) Parameter Sensitivity of Support Vector Regression and Neural Networks for Forecasting. In: Proceedings of international conference on data mining DMIN’06, pp 396–402

  44. 44.

    Hsu C-W, Chang C-C, Lin C-J (2016) A practical guide to support vector classification. https://www.csie.ntu.edu.tw/cjlin/papers/guide/guide.pdf

  45. 45.

    Han S, Qubo C, Meng H (2012) Parameter selection in SVM with RBF kernel function. In: Proceedings of the world automation congress 2012, Mexico

  46. 46.

    Bărbulescu A, Băutu E (2010) Mathematical models of climate evolution in Dobrudja. Theor Appl Climatol 100(1–2):29–44

    Article  Google Scholar 

  47. 47.

    Ferreira C (2001) Gene expression programming: a new adaptive algorithm for solving problems. Nonl Phen Compl Syst 13(2):87–129

    MathSciNet  MATH  Google Scholar 

  48. 48.

    Ferreira C (2006) Gene expression programming: mathematical modeling by an artificial intelligence. Springer, Berlin

    Google Scholar 

Download references

Acknowledgements

The work of the first author, Dana Simian, was supported from the “Lucian Blaga” University of Sibiu research Grant LBUS-IRG-2015-01. The work of the second author, Florin Stoica, was supported from the “Lucian Blaga” University of Sibiu research Grant LBUS-IRG-2015-01.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Dana Simian.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Simian, D., Stoica, F. & Bărbulescu, A. Automatic optimized support vector regression for financial data prediction. Neural Comput & Applic 32, 2383–2396 (2020). https://doi.org/10.1007/s00521-019-04216-7

Download citation

Keywords

  • Prediction methods
  • Support vector regression
  • Evolutionary computation
  • Financial forecasting
  • Genetic algorithms