Asset allocation decision involves bringing together estimates of current capital conditions and investor considerations in order to determine the asset allocation mix that will provide maximum utility to the investor. This can be accomplished by either maximizing return for a given risk level or by minimizing the risk for a given return objective. The purpose of this study is to develop a prototype decision support system that will provide a model for an investor to use in determining the optimal asset allocation for an investment portfolio at a particular risk level. This DSS consisted of five primary components. In this paper, we limited our discussion to the neural network (NN) component. The results of NN model can then be used as input to a quadratic programming model to determine the optimal asset allocation.