HOSPITAL MANAGEMENT SYSTEM: HUMAN RESOURCES 2 (LEARNING MANAGEMENT AND TRAINING MANAGEMENT, SUCCESS PLANNING) WITH RECOMMENDATION SYSTEMS USING TENSORFLOW

Abstract

In the dynamic landscape of hospital operations, human resource management plays a crucial role in ensuring that healthcare professionals are not only well-trained but also aligned with institutional goals. Traditional systems often lack intelligent recommendations and actionable insights, resulting in inefficiencies in training pathways and succession planning. To address this gap, this study proposes an advanced Hospital Management System: Human Resources 2, which integrates learning management, training management, and succession planning, enhanced by TensorFlow-based recommendation systems. The goal is to develop a data-driven, AI-powered HR system that personalizes employee learning paths, aligns training with organizational objectives, and supports long-term success planning within the healthcare environment. The system was developed using a microservices architecture with a modular PHP-based backend integrated with a MySQL database. Front-end components were built using HTML5, CSS3, and JavaScript. TensorFlow was utilized to develop a collaborative filtering recommendation engine that analyzes user interactions, training history, and performance evaluations to deliver personalized learning content and career development plans. The Agile Scrum methodology guided the system’s iterative development, incorporating stakeholder feedback and enabling continuous refinement. Key HR processes mapped in the system include training analysis, workshop planning, and performance and leadership tracking. The result was a functional and scalable hospital HR system that delivered customized training recommendations, predicted employee growth trajectories, and optimized the use of training resources. Powered by TensorFlow, the recommendation engine achieved an accuracy rate of over 87% during internal testing and showed strong relevance in recommended courses and career development opportunities. Additionally, the implementation reduced manual time spent on training assignments by 40%, improved employee satisfaction scores related to professional growth by 32%, and increased overall utilization of hospital-wide training modules by 58%. These outcomes support the adoption of AI as a transformative technology for HR functions in the healthcare sector. Compared to existing HRIS platforms, this system distinguishes itself by leveraging machine learning to deliver skill-based training recommendations, effectively reducing HR workload and boosting employee participation. Built-in scalability and security features ensure the system is well-prepared for real-world deployment in hospital environments.