ANALYSIS OF STOCK MARKET PREDICTION FOR INCORPORATING STOCK PRICES USING MACHINE LEARNING

When looking at a financial time series, the analysis of stock prices is becoming a topic that is
receiving a growing amount of attention. The purpose of the study is to carry out an examination
into the price of the stock exchange and the price criteria linked with it. These pricing criteria
include the date, high, and low prices, as well as news feed. In this study, the Long-Short Term
Memory Model is described. An exponential moving average was applied to it in order to carry
out an investigation of the price fluctuations that occurred in the stock market over a period of ten
and twenty days. Because it makes use of technical signals of price, this technique delivers higher
performance when compared to other approaches. Predicting the behavior of the stock market,
with all of its intricacies and constantly shifting circumstances, has always been a challenging
endeavor. As a consequence of the many studies that have been conducted in order to develop
correct prediction models, machine learning algorithms have emerged as powerful tools in this
area. These studies have been carried out in order to construct accurate prediction models. Within
the scope of this investigation, we propose a method for predicting the behavior of the stock
market that is based on the use of machine learning methods; one component of this prediction is
the utilization of current stock values.The first thing that has to be done in order to implement this
approach is to collect a historical database of information pertaining to the stock market. This
database should include information such as stock prices, trading volume, company-specific
news, and any other relevant indications. For the aim of training machine learning models, there
are a number of different preprocessing phases that are carried out. Some of these stages include
data cleaning, normalization, and feature engineering. These stages are carried out in order to
assure the correctness and usefulness of the data that will be used.