Forecasting stock market behavior is a complex and dynamic task, primarily due to the volatile, nonlinear, and multifactorial characteristics of financial data. This paper provides a comprehensive synthesis of recent research on artificial intelligence-based predictive modeling techniques for stock market analysis. By reviewing studies conducted between 2012 and 2024, the paper evaluates a broad spectrum of approaches, including traditional statistical models, machine learning algorithms, deep learning architectures, and emerging generative AI techniques. The review identifies a notable transition from conventional methods, including ARIMA, SARIMA, and exponential smoothing, to advanced models such as Artificial Neural Networks (ANNs), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), Transformers, and hybrid architectures like the Temporal Fusion Transformer with Graph Neural Networks (TFT-GNN). These advanced models exhibit enhanced capabilities in capturing complex temporal patterns, nonlinear relationships, and interdependencies within financial data. In multiple studies, deep learning models surpass traditional approaches according to evaluation metrics such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The study also emphasizes the importance of integrating diverse data sources, including technical indicators, fundamental financial metrics, macroeconomic variables, and market sentiment derived from news and external signals. Hybrid and ensemble models that combine multiple techniques consistently show improved predictive performance. Additionally, newer approaches such as generative AI models (GANs, VAEs, and Transformer-based systems) reveal promising capabilities in modeling hidden structures and enhancing forecasting accuracy. Despite these advancements, challenges such as overfitting, data noise, computational complexity, and the need for large datasets persist. The findings suggest that while no single model guarantees consistent accuracy across all market conditions, AI-driven approaches significantly enhance the ability to forecast trends and support investment decision-making. Overall, this paper underscores the transformative role of artificial intelligence in financial forecasting and highlights future directions focused on hybrid modeling, relational learning, and big data integration to further improve prediction reliability in rapidly evolving market environments.
Artificial intelligence; Prediction; Finance; Deep learning Challenge Dataset; Classification.
International Journal of Trend in Scientific Research and Development - IJTSRD having
online ISSN 2456-6470. IJTSRD is a leading Open Access, Peer-Reviewed International
Journal which provides rapid publication of your research articles and aims to promote
the theory and practice along with knowledge sharing between researchers, developers,
engineers, students, and practitioners working in and around the world in many areas
like Sciences, Technology, Innovation, Engineering, Agriculture, Management and
many more and it is recommended by all Universities, review articles and short communications
in all subjects. IJTSRD running an International Journal who are proving quality
publication of peer reviewed and refereed international journals from diverse fields
that emphasizes new research, development and their applications. IJTSRD provides
an online access to exchange your research work, technical notes & surveying results
among professionals throughout the world in e-journals. IJTSRD is a fastest growing
and dynamic professional organization. The aim of this organization is to provide
access not only to world class research resources, but through its professionals
aim to bring in a significant transformation in the real of open access journals
and online publishing.