Improvement of Stock Price Prediction by Synthesizing Recurrent ANN Back Track Solver

Stock market is always multi-dimensional in nature. Artificial neural network techniques are used to form the prediction of different training set of variables. In our previous paper knowledge set is applied for selecting the resultant training set. ANN Back propagation method is one of the best techniques used for analysing the historical data set. We used back propagation as the prediction analyser, which is best for reducing noisy in the data set. In this paper, we propose a Back propagation based multi-layer neural networks with back track solver (BTS) to expedite the training set. This paper focuses on BTS united with the Back propagation multi-layered neural networks for stock prediction method to show how the interaction of training set will improve the forecasting of stock market closing price.