This project aims to predict stock market trends by combining three key analyses: Technical, Fundamental, and Sentiment. The system employs a holistic approach, utilizing stock market indicators for Technical Analysis, regression models fine-tuned for Fundamental Analysis, and a custom algorithm for normalizing and aggregating results. The inclusion of Sentiment Analysis enhances the predictive power, creating a robust framework for forecasting stock movements.
-
Technical Analysis: Incorporates various stock market indicators and metrics for understanding historical price movements and trends.
-
Fundamental Analysis: Utilizes regression models, fine-tuned with historical financial data, to evaluate a company's intrinsic value and growth potential.
-
Sentiment Analysis: Integrates sentiment analysis on news articles, social media, and financial reports to gauge market sentiment and its impact on stock prices.
-
Normalization Algorithm: A proprietary algorithm designed from scratch to normalize and aggregate results from both Technical and Fundamental analyses, ensuring a unified and consistent prediction model.
- Python 3.x
- Pandas, NumPy, Scikit-Learn, TensorFlow (for machine learning components)
- Natural Language Toolkit (NLTK) for Sentiment Analysis
- Matplotlib, Seaborn (for visualization)
- Clone the repository:
https://github.com/Rajas-Mateti/MarketProphet.git
- Install the required dependencies:
pip install -r requirements.txt
- Run the main prediction script:
python RunMe.py
python build_model.py
python predicting.py
Contributions are welcome! If you have suggestions, find bugs, or want to add new features, feel free to open an issue or submit a pull request.
This project is licensed under the MIT License.
- Special thanks to the open-source community for providing valuable tools and libraries.
Happy forecasting! 📈🚀