Abstract: The stock market is an interlinked and fast-changing financial ecosystem shaped by many economic, political and psychological forces. This thus creates considerable difficulty for both investor and analyst in accurately forecasting stock price movements. With the advent of AI in recent past a lot of research has focused on improving forecast precision for assisting in better trading decision making. The paper critically evaluates the previous research on AI-propelled stock market prediction in three main fields: Machine Learning (ML), Deep Learning (DL), and Reinforcement Learning (RL) methodologies. While machine learning techniques such as Support Vector Machines (SVM) and Random Forests stand out, the discussion also brings together recent developments in deep learning architectures like Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) networks. It also covers reinforcement learning approaches for optimizing automated trading schemes. The review demonstrates how sentiment analysis and hybrid architectures have an impact on predictive efficacy. It describes the main results, comparative evaluations and gaps that are found in the present research to provide a structured information on the recent evolution in this area. It's hoped that through this work, researchers and practitioners will find a treasure trove of knowledge when creating intelligent and effective stock market advisory systems.

Keywords: Artificial Intelligence, Deep Learning, Machine Learning, Reinforcement Learning, Stock Market Prediction, Trading Strategy.

Downloads: | DOI: 10.17148/IARJSET.2026.13209