This project aims to analyze the factors influencing Airbnb pricing across major European cities using advanced machine learning techniques. Our analysis covers variables like location, property types, and host factors to provide a comprehensive understanding of Airbnb pricing dynamics. This research contributes valuable insights for Airbnb hosts, travelers, and researchers interested in the economics of shared housing platforms.
The dataset includes 51,707 Airbnb listings from ten major European cities. Features include host details, property characteristics, and geographical coordinates. The dataset was sourced from Kaggle and has undergone rigorous preprocessing for analysis readiness.
- Data Cleaning: Removal of duplicates, handling of missing values.
- Feature Engineering: Development of new variables for deeper insights.
- Regression Analysis: Linear, polynomial, and interaction effects analyzed.
- Random Forest Modeling: Employed for its robustness in handling complex datasets and non-linear relationships.
- Detailed analysis of pricing trends across different cities and property types.
- Identification of key pricing determinants such as location proximity, property amenities, and host characteristics.
- Comparison of model performances with insights into the effectiveness of different analytical approaches.
- Trinath Sai Subhash Reddy Pittala - tpittal@g.clemson.edu
- Uma Maheswara R Meleti - umeleti@g.clemson.edu
- Hemanth Vasireddy - hvasire@g.clemson.edu