Stock market prediction using evolutionary support vector machines: an application to the ASE20 index

Article English OPEN
Karathanasopoulos, Andreas ; Theofilatos, Konstantinos Athanasios ; Sermpinis, Georgios ; Dunis, Christian ; Mitra, Sovan ; Stasinakis, Charalampos (2016)

The main motivation for this paper is to introduce a novel hybrid method\ud for the prediction of the directional movement of financial assets with an application\ud to the ASE20 Greek stock index. Specifically, we use an alternative computational\ud methodology named Evolutionary Support Vector Machine (ESVM) Stock Predictor\ud for modeling and trading the ASE20 Greek stock index extending the universe of the\ud examined inputs to include autoregressive inputs and moving averages of the ASE20\ud index and other four financial indices. The proposed hybrid method consists of a\ud combination of genetic algorithms with support vector machines modified to uncover\ud effective short term trading models and overcome the limitations of existing methods.\ud For comparison purposes, the trading performance of the ESVM stock predictor is\ud benchmarked with four traditional strategies (a Naïve strategy, a buy and hold\ud strategy, a MACD and an ARMA models), and a MLP neural network model. As it\ud turns out, the proposed methodology produces a higher trading performance, even\ud during the financial crisis period, in terms of annualized return and information ratio,\ud while providing information about the relationship between the ASE20 index and\ud DAX30, NIKKEI225, FTSE100, SP&500 indices.
  • References (7)

    Guyon, I. and Elisseef, A. (2003) An Introduction to Variable and Feature Selection. Journal of Machine Learning Research. 3, 1157-1182.

    Scholkopf, B., Mika, S., Burges, J. C., Knirsch, P., Muller, K.-R., Ratsch, G. and Smola, A. (1999) Input Space Versus Feature Space In Kernel-Based Methods, IEEE Transactions on Neural Networks, 10(5), 1000 - 1017.

    Scholkopf, B. and Smola, A.J. (2002) Learning with Kernels: Support Vector Machines, Regularization and Beyond, Cambridge, Mass: MIT Press.

    Theofilatos, K., Georgopoulos, E., Likothanassis, S., Mavroudi S. (2014) Computational Intelligence: Recent advances, perspectives and open problems, In: Computational Intelligence for Trading and Investment, Routledge. DOI: 978-0- 415-63680-3

    Vapnik, V. N. (2000) The Nature of Statistical Learning Theory, Springer, United States of America.

    Yeh, C., Huang, C., Lee, S. (2011) A multiple-kernel support vector regression approach for stock market price forecasting. Expert Systems with Applications. 38(3), 2177-2186.

    Yuan, F. (2012) Parameters Optimization Using Genetic Algorithms in Support Vector Regression for Sales Volume Forecasting, Applied Mathematics, 3(1), 1480 - 1486.

  • Similar Research Results (1)
  • Metrics
    No metrics available
Share - Bookmark