Comparison of Performance Analysis using Different Neural Network and Fuzzy Logic Models for Prediction of Stock Price

Abstract

Analysis and prediction of stock market is very interesting as this helps the financial experts in decision making and in turn profit making. In this thesis simple feed forward neural network (FFNN) model is initially considered for stock market prediction and its result is compared with Radial basis function network (RBFN) model, fuzzy logic model and Elman network model. A FFNN model can fit into any finite input-output mapping problem where the FFNN consists of one hidden layer and enough neurons in the hidden layer. RBFN are the Artificial Neural Networks (ANN) in which Radial Basis Functions (RBF) are used as activation functions. In this thesis, Levenberg-Marquardt Backpropagation algorithm is used to train the data for both FFNN and Elman network. For Fuzzy Logic, Sugeno type Fuzzy Inference System (FIS) is used to model the prediction process. Different Clustering methods are used to nd the optimal parameters of RBF. These techniques were tested with published stock market data of National Stock Exchange of India Ltd. for validation.