International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 09 | Sep 2024
p-ISSN: 2395-0072
www.irjet.net
Predictive Modeling of Stock Price Using Machine Learning Krishnanand Dept. of Computer Science and Engineering State University of New York at Buffalo Buffalo, New York , United States of America ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Making predictions in the stock market
newbies in the stock market, navigating its complexities and constantly shifting landscape can prove daunting. This often results in significant losses for beginners, so many people hesitate to invest in the stock market due to perceived risks.
involves intricate strategies and relies heavily on an individual's experience. It can be challenging to predict stock prices and determine which companies are worth investing in due to the unpredictable nature of the stock market. However, the use of machine learning in this process has become increasingly prevalent in recent years. In the past few decades, the stock market's highly theoretical and speculative nature has been studied by capturing and utilizing repetitive methods. This research paper delves into utilizing cutting-edge machine-learning techniques for stock price prediction. The aim is to heighten precision in forecasting and evaluate different methodologies. The proposed technique involves using various regressors, including the Decision Tree Regressor, Random Forest Regressor, XGB Regressor and others. We have used the standard indicator Root Mean Square Error (RMSE) to evaluate the models. A lower RMSE score indicates higher efficiency of the trained models. Additionally, the financial data comprises several factors, including data, volume, open and closing prices of stocks, etc. With these techniques, we aspire to acquire valuable insights into the stock market, enabling us to make more informed investment decisions.
Historically, there have been two primary approaches to predicting stock market trends. The first method is a quantitative analysis that involves examining historical data such as opening and closing prices, fluctuations, and other key metrics. This data is then analyzed to identify patterns and trends that can be used to project future market movements. The second method is a qualitative analysis that involves examining external factors such as company and market profiles, socio-economic conditions, and political factors. This approach often involves sentimental analysis, which seeks to determine how investors feel about certain stocks and the market. Financial analysts and investors have used both methods for many years to try to gain insight into the complex and ever-changing world of the stock market. Nowadays, advanced intelligence techniques such as Artificial Intelligence and Machine Learning are used to predict stock prices. There are primarily four types of machine learning.
1.INTRODUCTION The stock market is a wealth hub, with the equity capital markets serving as a platform for trading company shares. Participants who buy, sell, and exchange stocks are commonly referred to as traders. The equity market in the United States is the largest in the world and remains the deepest, with high levels of liquidity and efficiency. In 2023, it represented 42.5% of the total global equity cap of $108.6 trillion, a significant increase from 2019's $85 trillion equity. The concept of Stock Market Prediction involves the effort to anticipate or estimate the upcoming value of a specific stock, a particular market segment, or the overall market. It is a process that typically entails analyzing various market indicators, such as market trends, historical data, and economic factors, to try and project the future performance of the stock market. This is a crucial exercise for investors, as it aids them in making informed decisions about which stocks to buy, sell, or hold. Investors have always sought ways to enhance their investment performance, and for the longest time, this required years of practice and experience. However, for
© 2024, IRJET
|
Impact Factor value: 8.315
Supervised Learning
Unsupervised Learning
Semi-Supervised Learning
Reinforcement Learning
Fig -1: Types of Machine Learning
|
ISO 9001:2008 Certified Journal
|
Page 243