Hybrid Approach of Wavelet Transform and ANN for Stock Market Prediction

Abstract

Time series data analysis is today’s financial need which is to be predicted with highest accuracy. A stock market data with some input variables like open, low, high and close price may influence the accuracy of a predictive model, therefore, it is necessary to decide input and output parameters for the model. In this proposed work we have used hybrid of two techniques called Wavelet Transform and Artificial Neural Network (ANN) for prediction of BSE30 stock data. Mean Absolute Percentage Error (MAPE) measures the accuracy of model.