Stock Price Prediction using a Deep Learning Algorithm LSTM and Machine Learning

Abstract

The challenging task of predicting stock value need a solid algorithmic framework to determine longer-term stock values. [1] Cost predictions will be challenging since stock prices are connected by market nature. A potential approach utilizing market data to forecast stock price using machine learning approaches like recurrent neural network called Long Short Term Memory, where method values are adjusted for every piece of data using stochastic gradient In contrast to stock price prediction systems that are already on the market [4], our method will deliver accurate results. With various sizes of input data, the network is programmed and assessed to provide graphical outputs. It has never been easy to invest in a set of assets, the abnormality of the financial market does not allow simple models to predict the future values of assets with higher accuracy [2]. Machine learning, which involves actions that ordinarily need human intelligence are performed by computers, is currently a dominant trend in scientific research. The focus of this research is to create a model for forecasting future stock market values using recurrent neural networks (RNN), specifically the Long-Short Term Memory (LSTM) model. This paper's major objective is to evaluate the predictive power of machine learning algorithms and the degree to which epochs may enhance our model. Furthermore, an extensive comparative analysis was carried out to identify the direction of significance. The study would be helpful for emerging researchers to understand the basics and advancements of this emerging area, and thus carry-on further research in promising directions.