Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM62178
Volume:
10 |
4 |
April 2026
Pages:
1-9
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Artificial Intelligence and Data Science
IIMT College of Engineering
Department of Artificial Intelligence and Data Science
IIMT College of Engineering
Department of Artificial Intelligence and Data Science
IIMT College of Engineering
Department of Artificial Intelligence and Data Science
IIMT College of Engineering
Department of Artificial Intelligence and Data Science
IIMT College of Engineering
Abstract: This paper presents the design, development, and evaluation of an intelligent stock market prediction and advisory system integrated with a real-time Telegram-based interface for Indian stock indices such as NIFTY50, BANKNIFTY, and SENSEX. The proposed framework combines multiple analytical paradigms, including statistical time-series modeling, machine learning algorithms, deep learning architectures, and sentiment analysis techniques, within a unified ensemble-based pipeline. The system maintains a structured repository of approximately ten years of historical OHLCV (Open, High, Low, Close, Volume) data and continuously updates real-time stock prices at short intervals. Using this data, it generates actionable investment recommendations such as Buy, Hold, or Avoid, along with predicted price targets over a 90-day horizon, adaptive stop-loss thresholds based on volatility, confidence scores, and market condition indicators. The advisory outputs are delivered through an interactive Telegram bot, enabling users to access real-time insights with minimal effort. Experimental evaluation on selected NIFTY50 stocks shows moderate predictive performance, with an average directional accuracy of approximately 51%, along with acceptable error metrics such as MAPE and RMSE. Although the system currently relies on fixed hyperparameters and limited sentiment integration during backtesting, it successfully demonstrates a complete end-to-end automated advisory framework. The proposed solution is cost-effective, scalable, and particularly beneficial for retail investors, with strong potential for improvement through advanced optimization and real-time data integration.
KEYWORDS
This study proposes a unified financial forecasting and advisory framework that leverages multiple predictive methodologies to analyze market behavior, while delivering real-time, actionable insights to users through an accessible and interactive system interface. Evaluation conducted on 48 NIFTY50 stocks shows a directional accuracy ranging from 48% to 56%, with an average of 51%. Additional performance metrics include a Mean Absolute Percentage Error (MAPE) of 14.6% and a Root Mean Square Error (RMSE) of ₹290.41. Although the predictive accuracy is moderate, the system successfully demonstrates the feasibility of combining diverse modeling approaches—such as ARIMA, GARCH, LSTM, Random Forest, XGBoost, FinBERT, and VADER—within a unified and practical framework. The integration of a real-time Telegram bot enhances usability by providing instant access to predictions and portfolio insights. Overall, the system represents a cost-effective and user-friendly solution for retail investors. With further improvements in model optimization, data integration, and system deployment, it has the potential to evolve into a more accurate and reliable financial decision-support platform.
[1] Box, George, and G. M. Jenkins. "Analysis: Forecasting and control." San francisco 10 (1976). [2] Bollerslev, Tim. "Generalized autoregressive conditional heteroskedasticity." Journal of econometrics 31, no. 3 (1986): 307-327. [3] Breiman, L. "Random Forests Mach. Learn., 45 (1), 5–32." ed (2001). [4] Chen, Tianqi, and Carlos Guestrin. "Xgboost: A scalable tree boosting system." In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp. 785-794. 2016. [5] Patel, Jigar, Sahil Shah, Priyank Thakkar, and Ketan Kotecha. "Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques." Expert systems with applications 42, no. 1 (2015): 259-268. [6] Hochreiter, Sepp, and Jürgen Schmidhuber. "Long short-term memory." Neural computation 9, no. 8 (1997): 1735-1780. [7] Araci, Dogu. "Finbert: Financial sentiment analysis with pre-trained language models." arXiv preprint arXiv:1908.10063 (2019). [8] Hutto, Clayton, and Eric Gilbert. "Vader: A parsimonious rule-based model for sentiment analysis of social media text." In Proceedings of the international AAAI conference on web and social media, vol. 8, no. 1, pp. 216-225. 2014. [9] Aroussi, Ran. yfinance: Download market data from Yahoo! Finance’s API. 2024. [10] Toledo, Leandro. "Python-telegram-bot Documentation." URL: https://readthedocs. org/projects/python-telegram-bot/downloads/pdf/latest (2022)
Publication Date
5/1/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...