The Impact of AI-Based Employee Analytics on Predicting Turnover in Labor Intensive Organizations: A Case of a Tobacco-Related Foreign Organization

Abstract

Employee turnover is a major challenge for labor-intensive industries, affecting productivity, operational efficiency, and organizational stability. Traditional HR methods often fail to predict turnover proactively. This study examines the impact of Artificial Intelligence (AI)–based employee data analytics on predicting employee turnover in a tobacco-related foreign organization. Using quantitative research design, employee data—including job satisfaction, performance, compensation, overtime, and tenure—was analyzed through machine learning algorithms such as logistic regression, decision trees, and random forests. Findings indicate that AI-driven predictive analytics significantly enhances turnover prediction. The study highlights that AI integration in HR enables proactive workforce management, supports targeted retention strategies, and improves organizational performance. Implications for HR professionals include leveraging AI insights for timely interventions, optimizing working conditions, and ensuring ethical implementation of predictive technologies.