This project aims to predict a new user's first booking destination on Airbnb using machine learning techniques. By analyzing user demographics, web session logs, and other relevant data, we develop models to forecast the first travel destination from 12 potential outcomes. The project is based on the Airbnb New User Bookings dataset from Kaggle, leveraging exploratory data analysis, feature engineering, and multiple machine learning models to achieve high accuracy in predictions.
- Problem Statement
- Machine Learning Approach
- Data Source and Exploration
- Model Development and Evaluation
- Deployment using Streamlit
- Summary and Future Scope
To run this project locally, follow these steps:
Ensure you have Python 3.x installed on your machine. You will also need Jupyter notebooks or a similar Python environment to run the analysis scripts.
- Clone the repository to your local machine:
- Install the required Python packages:
- Open the Jupyter Notebook
AirBnB_Destination_Prediction.ipynb
to view the analysis and model development process. - To launch the Streamlit application, run:
The final model is deployed using Streamlit, creating an interactive web application that allows users to input their details and receive predictions on their first Airbnb booking destination. Visit the app at: Streamlit App
- Integration of additional datasets for enriched feature engineering.
- Exploration of advanced machine learning models and hyperparameter tuning for improved accuracy.
- Development of a more interactive and user-friendly web application.
For any queries or further information, please reach out to:
Shradhanjali Pradhan
Email: email
LinkedIn: linkedin
- Kaggle for providing the Airbnb New User Bookings dataset.
- NYC Data Science Academy for project inspiration and resources.