Vera is a comprehensive loan application analysis and prediction system built with Python and Streamlit. It provides tools for loan approval prediction, batch processing, data analytics, and synthetic data generation.
Process individual loan applications with detailed inputs and receive instant approval decisions with confidence scores and risk metrics.
Upload multiple loan applications via CSV for bulk processing and analysis.
Comprehensive data analysis tools including:
- Dataset overview and statistics
- Feature correlation analysis
- Distribution visualizations
- Missing value analysis
Generate realistic synthetic loan application data for testing and analysis purposes.
Custom visualization tools for deep diving into the data and understanding patterns.
- Clone the repository and enter the directory
git clone <repository-url>
cd vera/backend- Create and activate a virtual environment
python -m venv .venv
# Windows
.venv\Scripts\activate
# Linux/Mac
source .venv/bin/activate- Install dependencies
pip install -r requirements.txt- Run the application
streamlit run app.pyThe application will be available at http://localhost:8501
backend/
├── app.py # Main application file
├── model.py # Model loading and documentation
├── prediction.py # Prediction functionality
├── data_processing.py # Data processing utilities
├── eda.py # Exploratory data analysis
├── analysis.py # Data analysis tools
├── generator.py # Synthetic data generation
├── models/ # Trained model files
├── data/ # Dataset directory
└── notebooks/ # Jupyter notebooks for model development
- Python 3.13
- Streamlit
- Pandas
- NumPy
- Scikit-learn
- Plotly
- Seaborn
- Matplotlib
- Joblib