Machine Learning Models in Skills-based Succession Planning and its Perspective in Hospitality Management

The hospitality industry faces significant challenges in leadership continuity, workforce retention, and succession planning, necessitating the adoption of data-driven decision-making strategies. Traditional HRM approaches to leadership development often rely on subjective assessments and manual succession planning, which can lead to inefficiencies and biases. The research investigates ML-based integration for skills-based succession planning, which establishes predictive competency-based frameworks for leader development. The study combines supervised learning artificial Neural Networks and XGBoost, along with Random Forest, to perform unsupervised clustering through Gaussian Mixture Models and K-Means and Natural Language Processing to evaluate leadership readiness from performance metrics, skill development trends, and career advancement indicators. The research demonstrates that ML models boost leadership forecasting effectiveness where ANNs deliver the best prediction results (91%) and GMMs produce optimal workforce classification abilities. The NLP-based analysis detects developing leadership characteristics that match modern industry needs through the identification of digital competency alongside data-based approaches as well as sustainability-focused leadership management practices. The research analyzes ethical challenges related to AI in HRM through bias in algorithms and data protection issues and supports explainable AI (XAI) strategies for transparent, fair talent selection. The recommended AI-powered succession planning system drives hospitality organizations through an efficient solution for optimizing their workforce, planning career paths, and promoting sustainable leadership. The research contributes knowledge to AI-enhanced HRM literature while providing actionable findings about data-based succession planning that builds organizational strength and market leadership performance.