Performance of the cascade correlation neural network for predicting the stock price

The cascade correlation neural network structure is proposed in this paper, which is used to predicting the closing price of the stocks related to state bank of India at the end of the particular day. The underlying fact of any neural network architecture is to minimize the error between the original outcome and expected result of the problem, by adjusting its weights in the architecture to the possible level. One of the tested and existing benchmark standards to measure the performance initially is with the help of Back propagation network structure. The drawbacks we encounter with this method are many, including slow rate of training process. During the training phase, equally alarming but never identified by the user of architecture is under fitting/over fitting of iteration, that leads to memorizing the pattern in case of over fitting and inaccurate results by under fitting, in which both cases need the attention of the programmer for appropriate corrective measures. The optimum number of hidden neurons, still formed by a thumb rule is another factor for above inaccuracy hence cascade correlation network is a kind in which the number of neurons in the hidden layer is in augmented initially form the scratch and stopped at the optimum level is an alternative for the pitfall encountered in the earlier architecture.