Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65470
Volume:
10 |
6 |
Jun 2026
Pages:
1-4
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 Computer Engineering
Zeal College of Engineering and Research,Pune
Department of Computer Engineering
Zeal College of Engineering and Research,Pune
Department of Computer Engineering
Zeal College of Engineering and Research,Pune
Department of Computer Engineering
Zeal College of Engineering and Research,Pune
This paper presents the implementation and evaluation of Stock Sense, a full-stack web application that integrates machine learning forecasting models with a locally hosted large language model to provide intelligent stock market analysis, sentiment-driven advisory, and portfolio management capabilities. The system employs a decoupled architecture comprising a Next.js 15 frontend, a Django REST Framework backend, and a hybrid database layer combining SQLite for relational transaction data with MongoDB for document-oriented financial data. Stock price forecasting is achieved through an ensemble of models—ARIMA, Exponential Moving Average (EMA), XGBoost Regression, and Long Short-Term Memory (LSTM) networks—while financial news sentiment classification utilizes a Bidirectional LSTM neural network and an XGBoost classifier. Natural language interaction is powered by the DeepSeek R1:1.5b model served locally through Ollama, enabling contextual financial advisory without external API dependency. Experimental evaluation on 163 processed news articles yields an XGBoost classification test accuracy of 87.88% for news nature prediction, while stock price forecasting across 30 NIFTY stocks demonstrates model-specific performance characteristics, including a negative R² score for short-horizon XGBoost price regression.
KEYWORDS
StockSense demonstrates the feasibility of combining multiple traditional forecasting models, custom neural network NLP classifiers, and locally hosted large language models to construct a comprehensive financial advisory platform. Although the quantitative price forecasting models highlight the classic difficulty of short-term market forecasting, the integrated sentiment-driven alerting, data scraping pipelines, and privacy-preserving local LLM advisory establish a robust architectural blueprint for modern intelligent trading dashboards.
[1]. Lohar, K., Pahwa, P., Asthana, N. and Gautam, D., 2024, February. Stock Market Analysis Using Time Series with ARIMA Model. In 2024 2nd International Conference on Computer, Communication and Control (IC4) (pp. 1-5). IEEE. [2]. Zhang, M., 2021, September. Design of simulated stock forecasting trading system based on time series. In 2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE) (pp. 382-385). IEEE. [3]. Banerjee, P. and Nayak, R., 2024. Recommendations on Financial Models for Stock Price Prediction. SN Computer Science, 5(1), p.178. [4]. Dwivedi, S.A., Attry, A., Parekh, D. and Singla, K., 2021, February. Analysis and forecasting of Time- Series data using SARIMA, CNN and LSTM. In 2021 international conference on computing, communication, and intelligent systems (icccis) (pp. 131-136). IEEE. [5]. Rahman, M.H., Nahid, S.I., Al Fahad, I.H., Nahid, F.M. and Khan, M.M., 2021, October. Price prediction using LSTM based machine learning models. In 2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) (pp. 0453- 0459). IEEE [6]. Kumar, P. and Mallieswari, R., 2022, February. Predicting stock market price movement using machine learning technique: Evidence from india. In 2022 Interdisciplinary Research in Technology and Management (IRTM) (pp. 1-7). IEEE. [7]. Jakhar, Y.K., Sharma, P. and Ahmed, B., 2024, July. Stock Price Prediction by Using Machine Learning Techniques: A Study of TCS Ltd. In 2024 2nd International Conference on Sustainable Computing and Smart Systems (ICSCSS) (pp. 1256-1260). IEEE. [8]. Manasa, N., Praveenraj, D.W. and SR, L., 2023, December. Predictive Analytics for Stock Market Trends using Machine Learning. In 2023 4th International Conference on Computation, Automation and Knowledge Management (ICCAKM) (pp. 1-8). IEEE. [9]. Varaprasad, B.N., Kanth, C.K., Jeevan, G. and Chakravarti, Y.K., 2022, March. Stock Price Prediction using Machine Learning. In 2022 International Conference on Electronics and Renewable Systems (ICEARS) (pp. 1309-1313). IEEE. [10]. Vakayil, S., Juliet, D.S. and Vakayil, S., 2024, April. RAG-Based LLM Chatbot Using Deepseek-2. In 2024 7th International Conference on Devices, Circuits and Systems (ICDCS) (pp. 1-5). IEEE.
Publication Date
6/26/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
7
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...