Neural Computing & Applications

, Volume 10, Issue 2, pp 184–192

Financial Forecasting Using Support Vector Machines

  • Lijuan Cao
  • Francis E.H Tay

DOI: 10.1007/s005210170010

Cite this article as:
Cao, L. & Tay, F. Neural Comput & Applic (2001) 10: 184. doi:10.1007/s005210170010

The use of Support Vector Machines (SVMs) is studied in financial forecasting by comparing it with a multi-layer perceptron trained by the Back Propagation (BP) algorithm. SVMs forecast better than BP based on the criteria of Normalised Mean Square Error (NMSE), Mean Absolute Error (MAE), Directional Symmetry (DS), Correct Up (CP) trend and Correct Down (CD) trend. S&P 500 daily price index is used as the data set. Since there is no structured way to choose the free parameters of SVMs, the generalisation error with respect to the free parameters of SVMs is investigated in this experiment. As illustrated in the experiment, they have little impact on the solution. Analysis of the experimental results demonstrates that it is advantageous to apply SVMs to forecast the financial time series.

Keywords:Back propagation algorithm; Financial time series forecasting; Generalisation; Multi-layer perception; Support vector machines

Copyright information

© Springer-Verlag London Limited 2001

Authors and Affiliations

  • Lijuan Cao
    • 1
  • Francis E.H Tay
    • 1
  1. 1.Department of Mechanical and Production Engineering, National University of Singapore, SingaporeSG