Predicting Airbnb Prices in Munich: A Machine Learning Approach to Dynamic Pricing and Key Influencing Factors

This thesis investigates the key factors driving price formation on the Airbnb platform in Munich through a machine learning-based analysis. By leveraging large-scale listing data, the study aims to uncover how features such as location, property characteristics, host behavior, and guest feedback influence dynamic pricing. The machine learning approach enables both accurate prediction and interpretability of pricing patterns, offering a data-driven perspective on market dynamics. Beyond technical insights, the thesis also addresses the broader social implications of short-term rentals in urban areas, including affordability concerns and regulatory challenges.