Kummer, MichaelLind, Moritz2026-04-062026-04-062025-01-092024-12-16http://hdl.handle.net/10362/202054This thesis introduces a scalable dynamic pricing framework for short-term rentals, addressing challenges in fragmented, data-sparse markets. Combining machine learning-based forecasting (R² = 84%, residual = 3.74%) with targeted adjustments—Price Elasticity of Demand (PED), Lead Time Rate (LTR), Occupancy Delta Factor (ODF), and seasonality calibrations—it optimizes Average Daily Rate (ADR), boosting revenue and stabilizing occupancy. Testing shows elastic pricing excels in high-demand Austrian markets, while steadier adjustments suit stable German regions. Despite reliance on historical data, modular solutions enhance RevPAR for operators without advanced RMS. Future work includes localized calibration, long-term analysis, and real world A/B testinengDynamic ADR pricingmachine learningRevenue managementShort-term rentalshospitalitymaster thesis204134030