“Stock Price Prediction using Machine Learning”
Keywords:
volatile, investment, sophisticated, frontend, Trend Whisperer, participation.Abstract
In today's volatile financial markets, making informed investment decisions requires sophisticated analysis tools accessible to both novice and experienced investors. This project presents TrendWhisperer, an advanced stock prediction application that leverages machine learning algorithms to forecast stock price movements and provide actionable trading recommendations. The system integrates a React.js-based frontend with a Python FastAPI backend, powered by state-of-the-art LSTM neural networks for time-series forecasting.
The frontend delivers an intuitive dashboard where users can search for NSE-listed stocks, visualize historical performance, view detailed price predictions for 7-day and 30-day horizons, and receive BUY/SELL/HOLD recommendations with confidence metrics. The backend implements a comprehensive machine learning pipeline that processes historical stock data from Yahoo Finance, normalizes time-series inputs, generates predictions through trained LSTM models, and calculates confidence levels based on prediction stability.
Trend Whisperer employs a three-layer LSTM architecture with dropout regularization to capture complex temporal patterns in stock prices while preventing overfitting. The system features dual time-horizon predictions that allow investors to align forecasts with their trading strategies, whether short-term or medium-term. A sophisticated recommendation engine analyzes predicted returns to generate actionable investment signals based on statistically-derived thresholds.
The application prioritizes accessibility and user experience through responsive design principles while ensuring data security through JWT-based authentication. For advanced users, the platform provides detailed technical indicators and prediction explanations to enhance transparency and foster trust in the AI-generated insights.
Trend Whisperer bridges the gap between complex financial analysis and practical investment decision-making, democratizing access to advanced predictive tools that were previously available only to institutional investors, thus empowering retail investors in their market participation.
Downloads
References
Yang, H., Pan, Z., & Tao, Q. (2023). Explainable deep learning for stock market prediction: A hybrid approach with technical analysis and sentiment. IEEE Transactions on Neural Networks and Learning Systems, 34(5), 2121-2135.
Liu, G., & Wang, X. (2023). Transformer-based multi-scale feature fusion for stock trend prediction. Knowledge-Based Systems, 262, 110234.
Kim, T., & Kim, H.Y. (2022). Attention-based hybrid neural network for multi-step stock price forecasting. Expert Systems with Applications, 204, 117706.
Zhao, R., Chen, Y., & Li, J. (2022). FinRL-Meta: Market environments and benchmarks for data-driven financial reinforcement learning. Advances in Neural Information Processing Systems, 35, 16775-16790.
Jiang, W. (2021). Applications of deep learning in stock market prediction: recent progress. Expert Systems with Applications, 184, 115537.
Sezer, O.B., Gudelek, M.U., & Ozbayoglu, A.M. (2020). Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Applied Soft Computing, 90, 106181.
Siami-Namini, S., Tavakoli, N., & Namin, A.S. (2019). A comparative analysis of forecasting financial time series using ARIMA, LSTM, and BiLSTM. ArXiv, abs/1911.09512.
Brownlee, J. (2018). Deep Learning for Time Series Forecasting. Machine Learning Mastery.
Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654-669.
Zhang, J., Cui, S., Xu, Y., Li, Q., & Li, T. (2018). A novel data-driven stock price prediction framework based on deep learning. Information Sciences, 463-464, 115-136.
Nelson, D.M.Q., Pereira, A.C.M., & de Oliveira, R.A. (2017). Stock market's price movement prediction with LSTM neural networks. International Joint Conference on Neural Networks (IJCNN), 1419-1426.
TensorFlow Documentation. Retrieved from: https://www.tensorflow.org/api_docs
Keras Documentation. Retrieved from: https://keras.io/api/
React.js Documentation. Retrieved from: https://reactjs.org/docs/getting-started.html
FastAPI Documentation. Retrieved from: https://fastapi.tiangolo.com/
Yahoo Finance API Documentation. Retrieved from: https://pypi.org/project/yfinance/
PostgreSQL Documentation. Retrieved from: https://www.postgresql.org/docs/
TimescaleDB Documentation. Retrieved from: https://docs.timescale.com/
Chart.js Documentation. Retrieved from: https://www.chartjs.org/docs/latest/
Tailwind CSS Documentation. Retrieved from: https://tailwindcss.com/docs
JWT Authentication Guide. Retrieved from: https://jwt.io/introduction/
LSTM Networks for Time Series Prediction. Retrieved from: https://machinelearningmastery.com/lstm-for-time-series-prediction/
NSE (National Stock Exchange) Official Documentation. Retrieved from: https://www.nseindia.com/
Docker Documentation. Retrieved from: https://docs.docker.com/
Backtesting.py Documentation. Retrieved from: https://kernc.github.io/backtesting.py/
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
