Overview
This project is an end-to-end data science pipeline that analyses and predicts nightly Airbnb prices in Rome, using Inside Airbnb's public data.
Tech Stack
- Python: The language for the whole project, tested on 3.13.
- pandas / NumPy: Load, clean and transform the listings data
- Jupyter: The notebooks where the models are compared and explained.
- scikit-learn provides the Ridge baseline model, the cross-validation setup and the error metrics
- Streamlit: Runs the web dashboard and hosts the live site on Streamlit Community Cloud.
PythonPandasStreamlitLightGBMXGBoostCatBoostPlotly
Data Flow
The pipeline runs in stages, from the raw listings to the live dashboard:
Raw Data -> Cleaning -> Feature Engineering -> Model Comparison -> Explaining the Model -> Streamlit Dashboard