Machine learning insights into nurse retention through job satisfaction and financial incentives

The global nursing shortage has reached a critical inflection point, where the financial sustainability of healthcare institutions is increasingly determined by their ability to maintain a stable, high-quality workforce. This study investigates the structural determinants of nurse staffing quality—operationalized as an institutional-level proxy for retention capacity—by integrating financial incentives, workload demands, and job-satisfaction metrics into an advanced machine-learning framework. Using the comprehensive CMS Provider Information dataset (N = 15,640 nursing facilities), we developed and validated a predictive architecture comparing Random Forest, Support Vector Machines, and Histogram-based Gradient Boosting (HGB) models. Our analysis reveals a clear hierarchy of influence: while Financial Incentives and penalties (Total Fines, importance weight: 0.083) and Job Satisfaction Proxies (QM Rating, 0.079) serve as significant secondary drivers, the primary boundaries of staffing stability are governed by Workload and capacity constraints, specifically the Number of Residents (0.309) and Number of Certified Beds (0.287). The Gradient Boosting model emerged as the superior predictive tool (Balanced Accuracy: 0.42; Macro F1: 0.41), demonstrating that institutional scale and patient volume are the dominant predictors of staffing quality ratings. These findings suggest that financial interventions alone are insufficient; sustainable nurse retention requires a dual-strategy that aligns fiscal incentives with rigorous workload management and capacity optimization. By identifying these high-impact variables and explicitly acknowledging the limitations of proxy-based operationalization, this research provides a data-driven roadmap for policymakers and healthcare executives to mitigate turnover and enhance the financial and operational resilience of nursing care systems.