Digital Digital transformation in Human Resource (HR) operations has generated diverse workforce datasets, creating opportunities for intelligent employee performance prediction. This study proposes an integrated framework combining artificial intelligence, deep learning, and knowledge graphs to capture relationships among employee attributes, roles, skills, and workplace contexts. Unlike conventional metric-based approaches, the proposed framework uses relational patterns to identify complex and evolving factors influencing performance. The framework is evaluated using publicly available workforce datasets and compared with traditional statistical and machine learning methods based on prediction accuracy, sensitivity, specificity, computational efficiency, scalability, and adaptability. Results demonstrate improved predictive performance, particularly in complex, noisy, and high-dimensional data environments, while maintaining stable performance under increasing workloads. Knowledge-graph integration also improves the interpretability of decision pathways. The proposed approach provides a scalable and adaptive solution for workforce analytics, supporting proactive performance management, talent development, and strategic workforce planning. By integrating relational knowledge with deep learning, the framework advances intelligent HR analytics for dynamic enterprise environments
Download
Download XML