Stock Market Prediction using Long Short-Term Memory

Strategies of the stock market are widely complex and rely on an enormous amount of data. Hence, predicting stock prices has always been a challenge for many researchers and investors. Much research has been done, and many machine learning techniques have been developed to solve complex computational problems and improve predictive capabilities without being explicitly programmed. This research attempts to explore the capabilities of Long Short-Term Memory a type of Recurrent Neural Networks in the prediction of future stock prices. Long Short-Term Memory variations with single and multiple feature models are created to predict the value of S\&P 500 based on the earnings per share and price to earnings ratio.