Digital Twins in Hospitality Management: Simulation-Based Decision Models for Efficiency Optimization in Central Europe

Abstract

Research background: Hotel operators benefit from evidence-based guidance for digital twin investment decisions, including quantified performance expectations across operational, financial, and sustainability dimensions. The study demonstrates digital twins' capacity to enhance profitability while advancing Industry 5.0 sustainability objectives by reducing energy consumption and optimizing resource allocation. Implementation requires comprehensive change management that addresses upfront capital requirements (€28,560 on average), IoT infrastructure deployment, and organizational readiness for simulation-driven decision-making. This research provides the first systematic empirical analysis of digital twin applications specifically designed for hospitality management in Central European markets, extending knowledge beyond manufacturing and smart building domains. The visualization-rich approach offers a practical framework for simulation-based operational optimization while contributing to Industry 5.0 literature on human-centric, sustainable technology integration in service sectors. Purpose of the article: This study examines the effectiveness of digital twin implementation in Central European hotel operations, focusing on simulation-based decision-support capabilities for energy optimization, staff productivity enhancement, and improved occupancy forecasting accuracy. Methods: A visualization-oriented case study methodology analyzed digital twin simulations across ten mid-scale and upscale hotels (3-4 star categories) in the Czech Republic, Slovakia, Poland, and Hungary during January to June 2025. The research integrated Building Information Modelling data, Internet of Things sensor networks, and property management system analytics to create dynamic operational models. The comparative analysis evaluated simulation predictions against actual performance metrics, including occupancy patterns (90-day forecasting), energy consumption (kWh per room night), and staff efficiency (labor hours per occupied room). Return on investment calculations incorporated implementation costs, operational benefits, and five-year discounted cash flow projections. Findings & Value added: Digital twin simulations demonstrated strong predictive accuracy, with an occupancy forecasting correlation coefficient (R²) of 0.86 and energy consumption variance within 8.3% of measured values. Energy optimization simulations identified HVAC control strategies that reduced consumption by an average of 11.5% (from 287.5 kWh/m²/year to 254.3 kWh/m²/year post-implementation) with 98.7% simulation accuracy. Staff productivity improvements averaged 14.7% through occupancy-driven scheduling optimization. Financial analysis confirmed investment viability, with a 3.4-year payback period and a 5-year cumulative benefit of €13,440 per property.