Divination of stock market exploration using long short-term memory (LSTM)

Abstract

In this modern era, there is a significant rise in stock market price which attracts the shareholders of the company. The shareholders, as well as the investor, show a great interest in the analysis and prediction of the stock market which eventually makes the investors and other speculators invest some good fortune in the company. A good prognosis may result in meaningful benefits. In today's life, more optimized models and different outlooks and analyzing trends are created over time. The analyzing framework used in this work is Long Short-Term Memory (LSTM) which is a part of Recurrent Neural Network (RNN) for long term dependencies. With the use of these algorithms with proper parameters precise results can be obtained. This can be done by collecting a dataset that consists of stock market data with all the opening and closing prices of stock having to be measured with several hidden layers and different units. With the result of this method, a more accurate prediction of the stock market is possible with historical datasets.