Digital twin-driven decision support for human capital management under uncertainty

Organizations increasingly face uncertainty in workforce planning, driven by shifting skill demands, rising turnover risks, and pressure to optimize labor investments. Traditional human capital decision models struggle to support strategic trade-offs among productivity, retention, and cost efficiency in dynamic environments. This study proposes a Digital Twin-driven decision support framework that enables adaptive, data-informed workforce optimization under uncertainty. The digital twin continuously mirrors employee profiles, performance trajectories, engagement patterns, and attrition risk, providing a real-time model of workforce dynamics. Using this live data environment, a multi-objective optimization model evaluates competing strategic outcomes, balancing productivity maximization, training and deployment cost minimization, and talent retention in critical roles. The framework is tested through simulation scenarios that reflect realistic organizational uncertainty, including fluctuating workloads, budget constraints, and employee movement. Results demonstrate that the system generates high-quality, interpretable decisions that achieve superior performance across all objectives compared to rule-based or single-factor decision strategies. The findings contribute to human capital analytics and digital transformation research by positioning digital twins as an intelligent capability enabling continuous workforce learning and decision refinement. Practically, the model offers organizations a scalable pathway to integrate real-time analytics, optimization, and predictive workforce intelligence into strategic HR planning.