Goodbye, scheduling nightmares! Hotel staff scheduling decision-making through synergistic optimization of GAI and swarm intelligence

Given the inefficiency and uncertainty associated with traditional manual experience-based scheduling in hotel industry, this study further improves hotel human resource allocation and operation efficiency through the design of staff scheduling decision system. Grounded in service-profit chain theory, this study proposes a dual-stage scheduling decision system, which incorporates customer demand prediction and schedule optimization through synergistic optimization of generative artificial intelligence (GAI) and swarm intelligence. An empirical study is executed in a popular Chinese hotel chain, which demonstrates that our system achieves lower labor expenses and schedule implementation modification costs compared to the existing man-made one and several popular baseline models. This study seeks to advance both theoretical understanding and practical forward-looking decision-making of staff scheduling in service industries.