Dynamic staff scheduling optimization algorithm for hotel management.

Area of Science:

• Operations Research
• Artificial Intelligence in Hospitality
• Management Science

Background:

• Traditional hotel staff scheduling relies on manual methods, leading to inefficiencies like overstaffing and service gaps due to fluctuating occupancy and demand.
• Dynamic challenges in hotel management require advanced solutions beyond experiential decision-making.

Purpose of the Study:

• To develop a staff scheduling algorithm for mid-range hotels that integrates dynamic demand forecasting and multi-objective optimization.
• To address inefficiencies in traditional scheduling by minimizing costs, service losses, and maximizing employee satisfaction.

Main Methods:

• Utilized Long Short-Term Memory (LSTM) for predicting departmental labor demands.
• Developed a multi-constraint mathematical optimization model with objectives including cost reduction, service quality improvement, and employee satisfaction.
• Employed an improved Genetic Simulated Annealing Algorithm (GASA) for solving the optimization model.

Main Results:

• Achieved a 15.3% reduction in daily operating costs and a 58.7% decrease in customer waiting time during high occupancy (90%).
• Reduced average employee overtime by 65.7% and lowered customer complaint rates by 78.3%.
• Demonstrated a rapid response time (<5 min) and 92% accuracy in adjusting schedules for sudden demand scenarios.

Conclusions:

• The proposed algorithm provides a quantitative tool for dynamic staff scheduling in hotel management.
• Offers valuable insights for multi-objective resource optimization in economy hotels facing similar operational scales and demands.