Literature Survey Paper on Predictive Analysis of Financial Markets

Abstract

Financial markets are highly volatile and influenced by various economic, social, and geopolitical factors. Predictive analysis in financial markets involves the application of statistical models, machine learning, and deep learning techniques to forecast market trends and asset prices. This survey explores the different methodologies used in predictive analysis, including traditional statistical models like ARIMA, machine learning algorithms such as Random Forest and Support Vector Machines (SVM), and deep learning approaches like Long Short-Term Memory (LSTM) networks. Additionally, sentiment analysis of financial news and social media data is also integrated to enhance forecasting accuracy. This paper presents a comparative analysis of these methods, their advantages, limitations, and future research directions in financial market prediction.