Stock Market Prediction Using Machine Learning and Deep Learning: A Systematic Literature Review

Abstract

Stock market prediction has emerged as one of the most challenging and important research areas in finance and artificial intelligence. Accurate prediction of stock prices enables investors, financial institutions, and policymakers to make informed investment decisions and manage financial risks effectively. Traditional statistical forecasting models have shown limited performance due to the nonlinear, dynamic, and highly volatile nature of financial markets. In recent years, Machine Learning (ML), Deep Learning (DL), and Artificial Intelligence (AI) techniques have significantly improved prediction capabilities by learning complex relationships from historical market data, technical indicators, fundamental information, and textual sentiment extracted from news and social media. This review systematically examines recent developments in stock market prediction, focusing on traditional statistical models, machine learning algorithms, deep learning architectures, hybrid approaches, reinforcement learning, and transformer-based models. The paper also discusses commonly used datasets, evaluation metrics, challenges, and future research directions. The review provides researchers with a comprehensive understanding of current methodologies and emerging trends in intelligent financial forecasting.