Lstm Based Deep Learning Approach For Stock Price Prediction

Abstract

Stock market strategies are highly sophisticated and rely on massive amounts of data. It has been a tedious task for many experts and investors to analyze and calculate stock prices in the future. Many machine learning techniques have been found to deal with complicated computational problems and efficient predictive methods without any complex programming. This study aims to investigate the capabilities of Long Short-Term Memory, a form of Recurrent Neural Network, in predicting future stock values. The prediction of LSTM is also compared with KNN, SVM, and RNN models. This paper uses three years' data of different companies such as Adani ports, Asian paint, Axis Bank, Cipla, Hcltech, Hdfc, and Titan. MSE and R2 measures are used to compare results.