Optimal partition algorithm of the RBF neural network and its application to financial time series forecasting

A novel neural-network-based method of time series forecasting is presented in this paper. The method combines the optimal partition algorithm (OPA) with the radial basis function (RBF) neural network. OPA for ordered samples is used to perform the clustering for the samples. The centers and widths of the RBF neural network are determined based on the clustering. The difference of the objective functions of the clustering is used to adjust the structure of the neural network dynamically. Thus, the number of the hidden nodes is selected adaptively. The method is applied to stock price prediction. The results of numerical simulations demonstrate the effectiveness of the method. Comparisons with the hard c-means (HCM) algorithm show that the proposed OPA method possesses obvious advantages in the precision of forecasting, generalization, and forecasting trends. Simulations also show that the OPA–orthogonal least squares (OPA–OLS) algorithm, which combines OPA with the OLS algorithm, results in better performance for forecasting trends.

[1]  Johan A. K. Suykens,et al.  Financial time series prediction using least squares support vector machines within the evidence framework , 2001, IEEE Trans. Neural Networks.

[2]  Miin-Shen Yang,et al.  Alternative c-means clustering algorithms , 2002, Pattern Recognit..

[3]  Renate Sitte,et al.  Analysis of the predictive ability of time delay neural networks applied to the S&P 500 time series , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[4]  Kyoung-jae Kim,et al.  Financial time series forecasting using support vector machines , 2003, Neurocomputing.

[5]  Francis Eng Hock Tay,et al.  Financial Forecasting Using Support Vector Machines , 2001, Neural Computing & Applications.

[6]  S. Chen,et al.  Multi-output regression using a locally regularised orthogonal least-squares algorithm , 2002 .

[7]  Randall S. Sexton,et al.  The Use of Parsimonious Neural Networks for Forecasting Financial Time Series , 1998 .

[8]  Guoqiang Peter Zhang,et al.  An investigation of model selection criteria for neural network time series forecasting , 2001, Eur. J. Oper. Res..

[9]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[10]  F. Tay,et al.  e-Descending Support Vector Machines for Financial Time Series Forecasting , 2002 .

[11]  F. Tay,et al.  Application of support vector machines in financial time series forecasting , 2001 .

[12]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[13]  C. Harris,et al.  Sparse multioutput radial basis function network construction using combined locally regularised orthogonal least square and D-optimality experimental design , 2003 .

[14]  Bernd Freisleben,et al.  Neural Network Model Selection for Financial Time Series Prediction , 2001, Comput. Stat..

[15]  Kevin Swingler.  Financial prediction: Some pointers, pitfalls and common errors , 2005, Neural Computing & Applications.

[16]  John A. Woollam,et al.  Use of Raman scattering to investigate disorder and crystallite formation in as-deposited and annealed carbon films , 1984 .

[17]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[18]  Francis Eng Hock Tay,et al.  ε-Descending Support Vector Machines for Financial Time Series Forecasting , 2002, Neural Processing Letters.

[19]  Phillip R. Burrell,et al.  The impact of neural networks in finance , 1997, Neural Computing & Applications.

[20]  Robert F. Ling,et al.  Cluster analysis algorithms for data reduction and classification of objects , 1981 .

[21]  M. Goldstein,et al.  Multivariate Analysis: Methods and Applications , 1984 .