The Complex Relationship Between Sleep Quality and Job Satisfaction: A Machine Learning-Based Bayesian Rule Set Algorithm

In today's highly competitive and rapidly evolving work environment, employee job satisfaction is a crucial indicator of organizational success and employee well-being. Utilizing the Bayesian rule set (BRS) algorithm, this study systematically explored how multiple variables, such as sleep quality, autonomy, and working hours, interact to influence job satisfaction. Based on an analysis of 618 data points from the CGSS database, we found that a single variable alone is insufficient to significantly improve job satisfaction: instead, a combination of multiple factors can substantially enhance it. Specifically, individuals who are older, have medium to high levels of sleep quality, and work fewer hours report higher job satisfaction. Similarly, individuals with medium to high health levels, high autonomy, and shorter working hours also exhibit high job satisfaction. By employing a multivariable combination analysis approach, this study reveals the complex pathways that affect job satisfaction, providing new theoretical insights and practical guidance for organizations seeking to improve employee satisfaction.