Stock Market Prediction Based on Back Propagation Neural Network
Shweta Bhagat, Reena Pagare Madhuri Tade, Rupali Gainkar, Rutuja Jamdar · CiiT international journal of artificial intelligent systems and machine learning · 2011
This paper uses an innovative approach of Back Propagation neural network algorithm to build a statistical market analysis tool to predict stock market. This paper presents the application of neural networks by establishing a three tier structure of the neural network, namely input layer, hidden layer, and output layer. With their ability to discover patterns in nonlinear and chaotic systems, neural networks are suitable to predict market trends. Input data to neural network are the widely used technical indicators like Moving average, Relative Strength Index, on balance volume, which are obtained from Yahoo Finance. The output simulated data will forecast the stock market by indicating whether the stock should be held bought or sold. The neural network approach provides a better predictive model to improve forecast accuracy.