Enhancing Strategy and Governance Through AI Driven Behavioural Competency Analytics: An ML Model for Competency Development

Strategic decision-making and organizational governance increasingly depend on accurate assessment of human behavioral competencies. Traditional evaluation methods often lack scalability, objectivity, and predictive insight, limiting their utility in dynamic enterprise environments. This study proposes a machine learning-based framework for competency development and analytics that integrates multi-source behavioral data with predictive modeling to enable data-driven governance. A structured pipeline is developed comprising behavioral signal attainment, feature engineering, probabilistic classification, and governance-aligned scoring. The framework is operationalized using multiple supervised learning models, including Logistic Regression, Random Forest, XGBoost, and Multilayer Perceptron, with XGBoost achieving the highest classification accuracy (83.4%) and superior probabilistic calibration. Cross-validation confirmed the robustness of performance with minimal variance (±1.5%), and interpretability was supported through feature attribution. Behavioral profiling revealed high central tendency in Analytical Thinking and wide dispersion in Ethical Conduct, informing strategic prioritization. The proposed model delivers calibrated, interpretable, and governance-compatible competency predictions, presenting a scalable solution for institutional leadership development, risk management, and policy alignment. Experimental validation across 1,247 behavioral instances confirms the model’s effectiveness in bridging human capital analytics with strategic decision processes.