A predictive analytics approach to mitigating employee turnover in Saudi Arabia community hotels

This study investigates a smart, multi-method framework designed to reduce employee turnover in community hotels in Saudi Arabia. Recognizing the hospitality industry's labor-intensive nature and the significant challenge of employee retention, particularly in resource-limited community hotels, this research integrates predictive analytics with qualitative insights and employee feedback. The framework aims to provide a comprehensive approach to understanding and addressing the causes of turnover. Key variables examined include perceived organizational support, job satisfaction, affective commitment, normative commitment, and turnover intention, with gender being a potential moderator. Predictive analytics employs a logistic regression model to forecast turnover risk and enable timely interventions. Findings indicate that perceived organizational diversity positively impacts job satisfaction and negatively affects turnover intention, with a notable moderation effect on gender. Female employees benefit more from diversity initiatives, experiencing higher job satisfaction and lower turnover intention, mediated by job satisfaction. The study emphasizes the value of fostering diversity and tailoring inclusion strategies to specific employee groups to enhance retention in the Saudi Arabian hospitality sector, aligning with Vision 2030's goals for tourism growth.