Much research on the applications of Neural Networks for solving business problems have proven their advantages over statistical and other methods that do not include artificial intelligence. Neural Networks methods, have become very important in making stock rate predictions (Gately and Edward, 1996). Results show that the use of neural network based backpropagation algorithm for predicting stock prices with two hidden layers are more accurate in comparison to single layer and three, four and five hidden layers.
Asif Ullah Khan, Mahesh Motwani , Sanjeev Sharma , Abdul Saboor Khan and Mukesh Pandey , 2007. Stock Rate Prediction Using Backpropagation Algorithm: Results with Different Number of Hidden Layers. Journal of Software Engineering, 1: 13-21.