Stock market prediction is a complex and challenging task due to the highly volatile and non-linear behavior of financial markets. This paper presents the design and implementation of an AI Based Stock Market Forecasting System — a real-time web application that integrates live market data retrieval, deep learning-based LSTM forecasting, Meta’s Prophet time-series model, technical indicator analysis (SMA, EMA, RSI), and real-time news sentiment scoring using TextBlob and NewsAPI. The proposed system is implemented using Python and Streamlit and provides an interactive dashboard with candlestick chart visualization, multi-model price prediction, RSI-based trading signals, per-user prediction history, and model comparison via RMSE. The system is designed for educational and research purposes and demonstrates how multiple AI techniques can be combined into a coherent, user-authenticated decision-support platform for stock market analysis.
Keywords
Stock Market Prediction, LSTM, Prophet Model, News Sentiment Analysis, Technical Indicators, Streamlit, Deep Learning, RSI, EMA, SMA.
Conclusion
This paper presented the design and implementation of an AI Based Stock Market Forecasting System, a comprehensive web application that integrates multiple artificial intelligence techniques within a unified, user-authenticated platform. The system combines LSTM deep learning networks for sequential price prediction, Meta’s Prophet model for trend and seasonality decomposition, RSI-based technical trading signals, and real-time news sentiment analysis to provide multi-perspective forecasts for publicly traded stocks. The proposed system successfully addresses the key limitations of single-model forecasting approaches by providing an empirical comparison framework that identifies the most accurate model for each specific stock and market condition. The modular architecture ensures that each component can be independently developed, tested, and extended without disrupting the rest of the system.
The interactive Streamlit interface, secure user authentication, persistent prediction history, and real-time news sentiment module collectively create a practical learning platform that bridges the gap between academic forecasting research and real-world algorithmic trading concepts. The system demonstrates how multiple AI disciplines — deep learning, time-series analysis, and natural language processing — can be integrated into a coherent decision-support tool.
Future work will focus on replacing the CSV backend with a production-grade database, integrating FinBERT for improved sentiment accuracy, extending the indicator library with additional technical signals, and adding a virtual portfolio simulation module. These enhancements will further strengthen the system’s utility as both an educational resource and a research platform for the study of AI-driven financial forecasting.
References
[1]J. J. Murphy, Technical Analysis of the Financial Markets, New York Institute of Finance, New York, NY, USA, 1999.
[2]S. Mohan, S. Mullapudi, S. Sammeta, P. Vijayvergia, and D. C. Anastasiu, “Stock price prediction using machine learning and deep learning frameworks,” in Proc. IEEE Int. Conf. Big Data, Los Angeles, CA, USA, 2019, pp. 381–389.
[3]J. Patel, S. Shah, P. Thakkar, and K. Kotecha, “Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques,” Expert Systems with Applications, vol. 42, no. 1, pp. 259–268, 2015.
[4]S. J. Taylor and B. Letham, “Forecasting at scale,” The American Statistician, vol. 72, no. 1, pp. 37–45, 2018.
[5]J. Bollen, H. Mao, and X. Zeng, “Twitter mood predicts the stock market,” Journal of Computational Science, vol. 2, no. 1, pp. 1–8, 2011.
[6]H. Wang, Z. Lei, X. Zhang, B. Zhou, and J. Peng, “A review of deep learning for renewable energy forecasting,” IEEE Access, vol. 7, pp. 131394–131415, 2019.
[7]S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, Nov. 1997.
How to Cite This Paper
Pothineni Prakash, Pasham Naga Sheshu, Pamidi Samba Siva Rao, Mrs.J.Fahamitha (2026). AI BASED STOCK MARKET FORECASTING SYSTEM. International Journal of Computer Techniques, 13(2). ISSN: 2394-2231.
