Machine Learning, Data Mining, Technical Analysis, Fundamental Analysis, Volatility Modeling.
Abstract
Stock price prediction has long been a focal point of research due to its significant implications for investors,traders, and financial analysts. With the advent of machine learning techniques, predictive models havebecome increasingly sophisticated, promising improved accuracy and robustness in forecasting future stockprices. This paper provides a comprehensive review of recent advancements in stock price prediction usingmachine learning methodologies. The review begins by discussing the fundamental challenges inherent in stock price prediction, includingmarket volatility, non-linearity, and the presence of noisy data. It then surveys the traditional time seriesanalysis techniques commonly employed in forecasting stock prices, such as ARIMA and GARCH models,highlighting their strengths and limitations. Subsequently, the paper explores the emergence of machine learning approaches, including regressionalgorithms, neural networks, and ensemble methods, which have shown promise in capturing complexpatterns and relationships within financial data. It examines various features and indicators utilized in thesemodels, ranging from technical indicators to sentiment analysis of news and social media data.
Article Details
Unique Paper ID: 164707
Publication Volume & Issue: Volume 10, Issue 12
Page(s): 2387 - 2392
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024