A Back Propagation Based Network Model for Forecasting Stock Market Movement

Machine Learning and Deep Learning algorithms are being extensively used for forecasting stock market trends. There are many different ways to forecast a market: from quantitative models and machine learning algorithms to technical analysis, which examines past price and volume data, to fundamental analysis, which assesses a company’s financial stability. Forecasts on the stock market should be viewed cautiously by analysts and investors due to the limits and potential biases of the methodology employed. It is often advised to use risk management, diversification, and a long-term outlook to deal with the inherent volatility of financial markets. This paper presents a back propagation based deep neural network model with data pre-processing for stock market forecasting. The results in terms of percentage error clearly indicate that the proposed approach performs better than existing work in the domain.