A stock price prediction platform built using Flask, React, and Python, providing users with up-to-date predictions and analysis with statistical and deep learning models like ARIMA, Regression, LSTM, and CNN.
- Flask: Micro web framework for building web applications in Python.
- React: JavaScript library for building user interfaces.
- Python: Programming language used for backend logic and machine learning models.
- TensorFlow, Keras, Scikit-learn: Libraries for implementing machine learning models.
- Pandas: For effective data preprocessing and analysis.
- Docker: Containerization for deployment.
- AWS: Cloud hosting and scaling.
- Real-time stock trend predictions leveraging ARIMA, GARCH, LSTM, and CNN models.
- Machine learning models developed with TensorFlow, Keras, and Scikit-learn for stock trend analysis.
- Pandas for efficient data preprocessing, enabling handling and analysis of vast financial data.
- Docker for streamlined deployment and scaling on AWS, ensuring reliable handling of user demand.
To start or clone the project, follow these steps:
-
Clone the Repository:
git clone https://github.com/your/repository.git
-
Navigate to the Project Directory:
cd project-directory
-
Start the Application:
docker-compose up
-
Access the Application: Open a browser and visit the appropriate URL to view the app.
Ensure the ports are correctly exposed and mapped within the docker-compose.yml
file according to your application's requirements. This setup uses Docker Compose to orchestrate the containerized services.
-
Clone the Repository:
git clone https://github.com/RaghavVerma24/StockBuddy.git
-
Navigate to the Project Directory:
cd StockBuddy
-
Install Dependencies:
-
Backend (Flask - Python):
cd flask-server pip install -r requirements.txt
-
Frontend (React):
npm install
-
-
Start the Servers:
-
Backend (Flask):
cd flask-server python server.py
-
Frontend (React/Vite):
npm run dev
-
Feel free to contribute to this project by submitting a pull request adhering to the project's coding standards and practices.
This project is open-source and available under the MIT License.