Stock Price Forecasting Using Deep Learning Model

Abstract

The successful prediction of future stock prices can give significant future profit. The financial experts are divided over the possibility of correct prediction of future stock prices. A stronger view supports the efficient market hypothesis, which suggests that current stock prices reflect all the available information, and it is not possible to predict the future stock prices. However, it is possible to predict the stock price trends. The proposed study presents a long short-term memory (LSTM) network model using sequence to sequence regression techniques to predict future stock prices. LSTM is a deep learning method. The study uses Aluminium Bahrain's (ALBA) ten-year stock price data from December 2010 to August 2021. The study concludes that using the LSTM model, it is possible to predict the trends for future stock prices. The model achieved an accuracy of root mean square error of 0.1684 during the training process and during the testing process, the RMSE accuracy achieved was 0.007. The study is expected to help investors, financial institutions, and financial market experts in predicting the trend of future stock prices.