Efficacy of a Classical and a Few Modified Machine Learning Algorithms in Forecasting Financial Time Series

  • Shilpa Amit VermaEmail author
  • G. T. Thampi
  • Madhuri Rao
Part of the Studies in Systems, Decision and Control book series (SSDC, volume 266)


Financial markets and economy forecast are closely related to each other. Forecast of prices of financial assets is therefore of importance for any economy-planning be it global, national or individual. There are various global, local and psychological factors that affect financial markets making its forecasting a non-trivial, complex problem. Numerous machine learning techniques have been applied by various researchers for a last few decades for making forecasts in various fields including the financial one, with varying degree of success. In the present article, time-series data of NIFTY50 of the National Stock Exchange (NSE) of India is considered as a reference data. Forecasting of its prices is done by applying the classical Gradient Descent Method (GDM) and by a few herein proposed modifications of it. The modifications are essentially using variants of the mean square error function of the classical GDM. All the proposed variants, Mean median (MMD) error function, Minkowski (MKW) error function, Logcosh (LCH) error function and Cauchy (CCY) error function, result in significant improvement in all the efficacy parameters of forecasting. Two widely varying time horizons, monthly and daily, have been considered. Significant enhancement in forecasting efficacy is obtained with the application of the Modified GDM methods in all the data sets: training, testing and out-of-sample.


Gradient descent method Forecasting Machine learning Stock market NIFTY50 Time series 


  1. 1.
    Jain, A., Bhatnagar, V.: Concoction of ambient intelligence and big data for better patient ministration services. Int. J. Ambient. Comput. Intell. (IJACI) 8(4), 19–30 (2017)CrossRefGoogle Scholar
  2. 2.
    Kamal, S., Dey, N., Nimmy, S.F., et al.: Evolutionary framework for coding area selection from cancer data. Neural Comput. Appl. 29(4), 1015–1037 (2018)CrossRefGoogle Scholar
  3. 3.
    Dey, N., Wagh, S., Mahalle, P., Pathan, M.: Applied Machine Learning for Smart Data Analysis. CRC Press, Boca Raton (2019).
  4. 4.
    Dey, N., Ashour, A.S., Bhatt, C.: Internet of things driven connected healthcare. In: Internet of Things and Big Data Technologies for Next Generation Healthcare, pp. 3–12. Springer, Cham (2017)Google Scholar
  5. 5.
    Mo, H., Wang, J., Niu, H.: Exponent back propagation neural network forecasting for financial cross-correlation relationship. Expert Syst. Appl. 53, 106–116 (2016)CrossRefGoogle Scholar
  6. 6.
    Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359–366 (1989)CrossRefGoogle Scholar
  7. 7.
    Dhar, V.K., Tickoo, A.K., Koul, R., Dubey, B.P.: Comparative performance of some popular ANN algorithms on benchmark and function approximation problems. Pramana 74(2), 307–324 (2010)CrossRefGoogle Scholar
  8. 8.
    Montgomery, D.C., Jennings, C.L., Kulahci, M.: Introduction to Time Series Analysis and Forecasting, 1st edn. Wiley, USA (2008)zbMATHGoogle Scholar
  9. 9.
    Kim, K.-j., Han, I.: Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index. Expert Syst. Appl. 19, 125–132 (2000)CrossRefGoogle Scholar
  10. 10.
    Kim, K.-j.: Financial time series forecasting using support vector machines. Neurocomputing 55, 307–319 (2003)CrossRefGoogle Scholar
  11. 11.
    Kim, K.-j.: Artificial neural networks with evolutionary instance selection for financial forecasting. Expert Syst. Appl. 30, 519–526 (2006)CrossRefGoogle Scholar
  12. 12.
    Abbasi, E., Abouec, A.: Sock price forecast by using neuro-fuzzy inference system. World Acad. Sci. Eng. Technol. 46, 320–323 (2008)Google Scholar
  13. 13.
    Atsalakis, G.S., Valavanis, K.P.: Forecasting stock market short-term trends using a neuro-fuzzy based methodology. Expert Syst. Appl. 36, 10696–10707 (2009)CrossRefGoogle Scholar
  14. 14.
    Boyacioglu, M.A., Avci, D.: An adaptive network-based fuzzy inference system (ANFIS) for the prediction of stock market return: the case of the Istanbul stock exchange. Expert Syst. Appl. 37, 7908–7912 (2010)CrossRefGoogle Scholar
  15. 15.
    Hadavandi, E., Shavandi, H., Ghanbari, A.: Integration of genetic fuzzy systems and artificial neural networks for stock price forecasting. Knowl.-Based Syst. 23, 800–808 (2010)CrossRefGoogle Scholar
  16. 16.
    Kara, Y., Boyacioglu, M.A., Baykan, Ö.K.: Predicting direction of stock price index movement using artificial neural networks and support vector machines: the sample of the Istanbul stock exchange. Expert Syst. Appl. 38, 5311–5319 (2011)CrossRefGoogle Scholar
  17. 17.
    Ticknor, J.L.: A Bayesian regularized artificial neural network for stock market forecasting. Expert Syst. Appl. 40, 5501–5506 (2013)CrossRefGoogle Scholar
  18. 18.
    Moghaddam, A.H., Moghaddam, M.H., Esfandyari, M.: Stock market index prediction using artificial neural network. J. Econ. Financ. Adm. Sci. 21, 89–93 (2016)Google Scholar
  19. 19.
    Aparna Nayak, M.M., Pai, M., Pai, R.M.: Prediction models for Indian stock market. Proc. Comput. Sci. 89, 441–449 (2016)CrossRefGoogle Scholar
  20. 20.
    Abdulmalik, S., Almasani, M., Finaev, V.I., Qaid, W.A.A., Tychinsky, A.V.: The decision-making model for the stock market under uncertainty. Int. J. Electr. Comput. Eng. (IJECE) 7(5), 2782–2790 (2017)CrossRefGoogle Scholar
  21. 21.
    Devadoss, A.V., Ligori, T.A.A.: Stock prediction using artificial neural networks. Int. J. Data Min. Tech. Appl. 2, 283–291 (2013)Google Scholar
  22. 22.
    Yetis, Y., Kaplan, H., Jamshidi, M.: Stock market prediction by using artificial neural network. World Automation Congress, pp. 718–722. IEEE Computer Society, U.S. (2014)Google Scholar
  23. 23.
    Qiu, M., Song, Y., et al.: Application of ANN for prediction of stock market returns: Case of Japanese stock market. Chaos Solitions Fractals 85, 1–7 (2016)Google Scholar
  24. 24.
    Kamley, S., Jaloree, S., Thakur, R.S.: Performance forecasting of share market using machine learning techniques: a review. Int. J. Electr. Comput. Eng. 6(6), 3196–3204 (2016)CrossRefGoogle Scholar
  25. 25.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)CrossRefGoogle Scholar
  26. 26.
    Atsalakis, G.S., Kimon, P., Valavanis, K.P.: Surveying stock market forecasting techniques—Part II: soft computing methods. Expert Syst. Appl. 36, 5932–5941 (2009)CrossRefGoogle Scholar
  27. 27.
    Reidmiller, M.: Advanced supervised learning in multilayer perceptrons from backpropagation to adaptive learning algorithms. Comput. Stand. Interfaces 16, 265–278 (1994)CrossRefGoogle Scholar
  28. 28.
    Moller, M.F.: A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw. 6, 525–533 (1993)CrossRefGoogle Scholar
  29. 29.
    Marquardt, D.W.: An algorithm for least square estimation of non-linear parameters. J. Soc. Ind. Appl. Math. 11(2), 431–441 (1963)CrossRefGoogle Scholar
  30. 30.
    Lahmiri, S.: A comparative study of backpropagation algorithms in financial prediction. Int. J. Comput. Sci. Eng. Appl. 1(4), 15–21 (2011)Google Scholar
  31. 31.
    Gangal, A.S., Kalra, P.K., Chauhan, D.S.: Performance evaluation of complex valued neural networks using various error functions. Int. J. Electr. Comput. Energ. Electron. Commun. Eng. 1(5), 732–737 (2007)Google Scholar
  32. 32. Accessed 10 April 2019

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Shilpa Amit Verma
    • 1
    Email author
  • G. T. Thampi
    • 2
  • Madhuri Rao
    • 2
  1. 1.Computer DepartmentMumbai University Thadomal Shahani Engineering CollegeBandraIndia
  2. 2.IT DepartmentMumbai University Thadomal Shahani Engineering CollegeBandraIndia

Personalised recommendations