A hybrid method for tuning neural network for financial time series forecasting

This paper presents an new hybrid method for financial time series prediction called GRASPES. It is based on the Greedy Randomized Adaptive Search Procedure(GRASP), which is a multi-start metaheuristic for combinatorial problems, and Evolutionary Strategies (ES) concepts for tuning of the structure and parameters of an Artificial Neural Network (ANN). The work proposed here consists of an ANN trained and adjusted by GRASPES, which is capable to evolve the parameters configuration and the weights of the ANN, searches for the minimum number of relevant time lags for a correct time series representation and found an optimal or sub-optimal forecasting model. An experimental investigation is conducted with the GRASPES with four real world financial time series and the results achieved are discussed and compared, according to five well-known performance measures, to other works reported in the literature, demonstrating the good performance of GRASPES for financial time series forecasting.

[1]  Lilian M. de Menezes,et al.  Forecasting with genetically programmed polynomial neural networks , 2006 .

[2]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[3]  Hak-Keung Lam,et al.  Tuning of the structure and parameters of a neural network using an improved genetic algorithm , 2003, IEEE Trans. Neural Networks.

[4]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[5]  Ying Wang,et al.  Time series study of GGAP-RBF network: predictions of Nasdaq stock and nitrate contamination of drinking water , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[6]  P. McNelis.  Neural networks in finance : gaining predictive edge in the market , 2005 .

[7]  A. E. Eiben,et al.  Introduction to Evolutionary Computing , 2003, Natural Computing Series.

[8]  Mauricio G. C. Resende,et al.  Greedy Randomized Adaptive Search Procedures , 1995, J. Glob. Optim..

[9]  Renate Sitte,et al.  Neural Networks Approach to the Random Walk Dilemma of Financial Time Series , 2002, Applied Intelligence.

[10]  A. Walden,et al.  The Econometric Modelling of Financial Time Series. , 1995 .

[11]  Tiago Alessandro Espínola Ferreira,et al.  A New Evolutionary Approach for Time Series Forecasting , 2007, 2007 IEEE Symposium on Computational Intelligence and Data Mining.

[12]  Tiago A. E. Ferreira,et al.  An Evolutionary Morphological Approach for Financial Time Series Forecasting , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[13]  João Paulo Carvalho,et al.  Market index prediction using fuzzy Boolean nets , 2005, Fifth International Conference on Hybrid Intelligent Systems (HIS'05).

[14]  F. Takens.  Detecting strange attractors in turbulence , 1981 .