Stock Price prediction using LSTM and SVR

Abstract

Stock price movement is non-linear and complex. Several research works have been carried out to predict stock prices. Traditional approaches such as Linear Regression and Support Vector Regression were used but accuracy was not adequate. Researchers have tried to improve stock price prediction using ARIMA. Due to very high variations in stock prices, deep learning techniques are applied due to its proven accuracy in various analytics fields. Artificial Neural Network was deployed to predict stock prices but as stock prices are time-series based, recurrent neural network was applied to further improve prediction accuracy. In RNN, there is limitation of not able to store high dependencies and also vanishing gradient descent issue exists. Therefore, data scientists and analysts applied LSTM to predict stock price movement. In this paper, LSTM is compared with SVR using various stock index data such as S& P 500, NYSE, NSE, BSE, NASDAQ and Dow Jones industrial Average for experiment analysis. Experiment analysis proves that LSTM provides better accuracy as compared to SVR.