The Prediction Stock Market Price Using LSTM

Abstract

In this paper, we will focus on the applicability of recurrent neural networks, particularly the Long Short Term Memory networks, in predicting the NASDAQ and the S&P 500 stock market prices were investigated. Daily stock exchange rates of NASDAQ and S&P 500 from January 4, 2010, to January 30, 2020, are used to construct a robust model. By building a model with various configurations of LSTM can be tested and compared. We used two evaluation measures, the coefficient of determination R2 as well as the “Root Mean Squared Error” RMSE, in order to judge the relevance of the results.