Would Evolutionary Computation Help in Designs of Artiicial Neural Nets in Forecasting Financial Time Series?

Since the pioneering work by White (1988), the application of artiicial neural networks (ANNs) to nance has enjoyed an exponential growth in research and publications. The evidences accumulated over the last decade indicate that the success of the nancial application of ANNs crucially depends on the design of the ANN. Let us rst consider the structure of the ANN. It is well known that nonlinear ARMA time series can be more eeciently approximated by recurrent neural nets than by their layered feedforward counterparts. Also, with the presence of structural switches in time, it may be more appropriate to use modular neural networks (Kimoto, Asakawa, Yoda, and Takeoka, 1990). The many successful applications of radial basis neural networks in nance further suggests the relevance of this special class of artiicial neural nets to nance (Hutchinson, Lo and Poggio, 1994). Once the structure has been decided, the next complicated task to deal with in the design of the ANN is the architectures. In this area, one of the most frequently discussed issues is the number of hidden nodes. It is widely accepted by nance people that the number of hidden nodes are closely related to the issue of overrtting, and that a proper choice of the number of hidden nodes (hidden layer size) can enhance the generalization capability of ANNs. Diierent techniques have been tried by researchers to control hidden layer size, among them, cross validation In contrast, the signiicance of transfer functions has received less attention among nance people in their design of ANNs. While the relevance of the transfer function to the design of ANNw has been shown earlier by Mani (1990), Lovell and Tsoi (1992) and, recently, by Sebald and Chellapilla (1998), its role in the nancial domain has not been well documented. Even though the radial basis network has been promoted, the choice of sigmoid, hyper tangent or radian basis functions seems to be based largely on the hunch of the researcher rather than the performance of each function. In their option pricing model, Hutchinson, Lo and Poggio (1994) compared the performance of the radial basis function and the sigmoid function and did not