Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{191927,
        author = {Shravanthi Ashwin kumar},
        title = {AI-Driven Hybrid Framework for Financial Forecasting Using Machine Learning and Time Series Models},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {8999-9006},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191927},
        abstract = {Financial forecasting remains a cornerstone of modern economic systems, driving investment strategies, risk management, and policy decisions. Traditional statistical models like ARIMA, while robust, often fall short in capturing the non-linear, high-dimensional nature of financial time series data. Conversely, machine learning and deep learning models—such as LSTM, XGBoost, and GRU—offer powerful alternatives but can lack interpretability and struggle with time dependencies. This review explores the emerging trend of AI-driven hybrid forecasting frameworks, which integrate traditional and AI-based models to leverage their complementary strengths. We provide a comprehensive synthesis of existing literature, present a proposed hybrid architecture, evaluate its performance using multiple datasets, and highlight key findings. Our results confirm that hybrid models consistently outperform individual models across standard forecasting metrics. We conclude by identifying critical future directions in the field, including explainability, online learning, and multi-modal data integration.},
        keywords = {Hybrid Forecasting Models, Financial Time Series, ARIMA, LSTM, XGBoost, Explainable AI},
        month = {January},
        }