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{185827,
        author = {Prof. Barvkar B.Y and Prof.Gawand R.R. and Ms.Rachna Dattatray Dongare and Ms.Snehal Nandkishor Dhulgande},
        title = {Predictive Analytics In Stock Market Trading},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {5},
        pages = {2941-2945},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=185827},
        abstract = {Stock markets are complex adaptive systems driven by myriad factors including macroeconomic indicators, investor sentiment, microstructure dynamics, and global events. Predictive analytics leverages statistical models, machine learning, and increasingly largescale language models to extract patterns from historical data and forecast future price movements. In this work, we examine the application of recent advances in artificial intelligence—particularly large language models akin to in enhancing predictive accuracy and decision-making in stock trading.
We introduce a hybrid framework combining quantitative time-series analysis (e.g., ARIMA, LSTM, Transformer-based models) with natural language processing (NLP) of financial news, social media, and regulatory disclosures. The model ingests both numerical data (prices, volumes, fundamental indicators) and textual data (news sentiment, earnings reports) to produce probabilistic forecasts of stock returns and risk metrics.
We validate the framework using historical data from major stock indices over multiple market regimes (bull, bear, and sideways markets). Our results show that incorporating textual features improves forecasting performance over purely numerical models, especially around high-impact events. We also analyze the trade-off between model complexity and overfitting, and address challenges such as data leakage, non-stationarity, and interpretability.},
        keywords = {Predictive analytics, Stock market prediction, financial forecasting, Time series analysis, Machine learning},
        month = {October},
        }