PREDICTING EMPLOYEE TURNOVER IN THE UNITED STATES: A COMPARATIVE MACHINE LEARNING ANALYSIS USING NATIONAL WORKFORCE SURVEY DATA (2010–2025)

Employee turnover remains one of the most significant workforce challenges affecting organizational productivity, competitiveness, and long-term sustainability. This study examined national employee turnover trends in the United States between 2010 and 2025 and comparatively evaluated the performance of machine learning algorithms for predicting employee turnover using harmonized data from nine nationally representative workforce datasets: JOLTS, CPS, ACS, NLSY97, LEHD, NCS, OEWS, O*NET, and SIPP. A comparative quantitative design integrating descriptive trend analysis, supervised machine learning, and Explainable Artificial Intelligence (SHAP) was employed. Seven classification algorithms: Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, Artificial Neural Network, Gradient Boosting Machine, and Extreme Gradient Boosting (XGBoost), were evaluated using cross-validation and multiple performance metrics. The results revealed three distinct labor market phases: post-recession recovery (2010–2019), COVID-19 disruption (2020), and post-pandemic adjustment (2021–2025), with workforce mobility remaining above historical levels despite recent stabilization. XGBoost achieved the highest predictive accuracy (92.8%), outperforming all other models, followed by Random Forest (91.6%) and Gradient Boosting (90.9%). SHAP analysis identified organizational tenure, annual wage, age, employee benefits, and regional job openings as the most influential predictors of employee turnover, while employment history and compensation emerged as the dominant predictor domains. The findings demonstrate that employee turnover is driven by the interaction of organizational, demographic, occupational, and labor market factors rather than isolated organizational characteristics. The study concludes that integrating nationally representative workforce data with machine learning and explainable artificial intelligence provides a robust framework for proactive employee retention, strategic workforce planning, and evidence-based labor market policy.