Abstract: A stock market is a place or a public market where you can sell or buy shares for all the publicly listed companies. The stocks have values and rights that represent ownership in the company. The stock exchange is the arbitrator which allows the buying and selling of shares. The future value of the company stocks and the other financial assets traded on an exchange can be done with the help of stock price prediction using machine learning. A significant amount of profit and gain can be done with the help of stock price prediction and that is the main reason behind that because predicting how the stock market will perform is a hard task to do.
There are many factors involved in the prediction, such as physical and psychological factors, rational and irrational behaviour, and so forth. These kinds of factors combine to make share prices volatile and dynamic. This makes it very hard to predict stock prices with high accuracy. There were numerous strategies or algorithms which we are able to select to build this project, for now we are going to use one of the famous topics of Machine Learning which are Long short-term memory (LSTM).
Long short-term memory (LSTM) is an artificial recurrent neural network (RNN) architecture used in the field of deep learning. Unlike conventional server neural networks, it has a feedback loop. It can process not only single data points such as images, but also whole data sequences such as speech or video. For example, LSTM works on tasks such as unsegmented, connected handwriting recognition, speech recognition and anomaly detection in network traffic or IDSs (intrusion detection systems). A standard LSTM unit is made up of a cell, an input gate, an output gate and a forget gate. The cell remembers numbers periodically and the three gates control the entry and exit of information from the cell. Linear Regression: In statistics, linear regression is a linear approach for modelling the relationship between a scalar response and one or more explanatory variables. In case for a single descriptive variable is called a simple linear regression; for more than one, the process is called multiple linear regression. This term is distinct from multivariate linear regression, in which multiple related dependent variables are predicted, rather than a single scalar variable.

Keywords: Recurrent Neural Network, Stock Price, Stock Price Prediction, Long Short-Term Memory

| DOI: 10.17148/IARJSET.2021.81140