Financial Models for Indian Stock Prices Prediction Using LSTM and Bi-Directional LSTM Model

Abstract

The Stock market is a large ocean of investors who sell and buy the stocks on daily basis resulting in drastic changes in the stock prices. The factors that affect the price of stock are the principles of demand and supply. The task of predicting the stock prices has been a tedious art on which the researchers and analysts have been working for years. The investors show a lot of interest in this  eld so that they can invest their assets in the right place. This can be done by knowing the future circumstances of the stock market. Precisely predicting the stock price variation in market is a massive economic bene t. This task is mostly accomplished by analyzing by any organization; is called as basic investigation. Another strategy, which is going through a great deal of exploration work as of late, is to make a predictive algorithmic model utilizing machine learning and deep learning.

This paper tends to build a model using architecture of Recurrent Neural Network (RNN) named Long Short-Term Memory (LSTM) to make predictions on future values of the stock. Deep Neural Networks, being the most extraordinary advancement in Machine Learning, have been used to foster an expectation model for securities exchange. This paper also discusses about two distinct sorts of Recurrent Neural Network, LSTM and Bi Directional LSTM model.