Artificial Intelligence-Driven Workforce Optimization: An Operational Research Framework for Strategic Human Resource Management and Organizational Decision-Making

Abstract

The increasing adoption of Artificial Intelligence (AI) has transformed strategic human resource management by enabling organizations to predict workforce outcomes more accurately. However, most existing studies focus primarily on employee attrition prediction and provide limited guidance for translating predictive insights into actionable workforce planning decisions. This study proposes an integrated Artificial Intelligence–Operational Research (AI–OR) framework for workforce optimization that combines machine learning, explainable AI, and mathematical optimization to support strategic human resource management and organizational decision-making. Two publicly available employee datasets comprising 16,189 employee records were analyzed using Logistic Regression, Decision Tree, Random Forest, XGBoost, and LightGBM algorithms. Model performance was evaluated using Accuracy, Precision, Recall, F1-score, ROC-AUC, PR-AUC, and Matthews Correlation Coefficient, with Random Forest demonstrating superior predictive performance across both datasets. SHapley Additive exPlanations (SHAP) were employed to identify the key determinants of employee attrition, enhancing model transparency and interpretability. Subsequently, a Mixed Integer Linear Programming (MILP) model was developed to optimize workforce intervention strategies under resource constraints. The optimization results demonstrated that targeted interventions directed toward a relatively small proportion of high-risk employees could mitigate a substantial share of organizational attrition risk while efficiently utilizing limited organizational resources. Sensitivity analysis further confirmed the robustness of the proposed framework under varying intervention capacities and effectiveness scenarios.