Stock Market Prediction Web App Developed with Streamlit

TODO: App Icon

This web application is designed to predict stock market trends using machine learning models and visualizing the results with Streamlit.

Features

• Interactive Dashboard: User-friendly interface to input stock symbols, select date ranges, and visualize predictions.

• Machine Learning Models: Utilizes the Prophet model from Facebook for time-series forecasting and scikit-learn for additional analysis.

• Data Retrieval: Fetches historical stock data using the yfinance library.

• Beautiful Visualizations: Presents predictions and historical data with interactive charts powered by Plotly.

Technologies Used

• Streamlit: The main framework for building the web application.

• Prophet: A forecasting tool from Facebook for time-series data.

• yfinance: Retrieves financial data, including stock prices.

• Plotly: Creates interactive and visually appealing charts.

• scikit-learn: Used for machine learning tasks.

Installation

1. Clone the repository:

   git clone https://github.com/abdellatif-laghjaj/stock-market-prediction-app.git

2. Install the required dependencies:

   pip install -r requirements.txt

3. Run the Streamlit app:

   Run the app normally:

   streamlit run main.py

   Or run the app on save mode:

   streamlit run main.py --server.runOnSave true

   Or run the app in debug mode:

    streamlit run main.py --server.runOnSave true --server.enableCORS false

4. Open your web browser and navigate to http://localhost:8501 to access the app.

Usage

1. Enter the stock symbol and select the date range.

2. Explore the interactive charts to analyze historical data.

3. View the predictions generated by the machine learning model.

Screenshots

TODO: App Screenshots

Contributing

Contributions are welcome! If you'd like to enhance the app or fix any issues, please open an issue or submit a pull request.

License

This project is licensed under the MIT License.

Acknowledgments

• Special thanks to the creators of Streamlit, Prophet, yfinance, Plotly, and scikit-learn.

Happy predicting!