Enhancing HR Onboarding Efficiency and Predicting Employee Success with Graph Neural Network

Human Resources (HR) onboarding is a critical step in integrating new employees into an organization. Effective onboarding can improve employee satisfaction, reduce turnover, and accelerate productivity. However, traditional methods for onboarding and predicting employee success are often limited to individual-level attributes, neglecting the complex network of relationships and team dynamics that influence an employee's experience. The proposed framework exploit Graph Neural Networks to enhance HR onboarding efficiency and predict long-term employee success. Thus, demonstrating the IBM HR Analytics Employee Attrition & Performance dataset by constructing a graph: nodes are employees, and edges denote relationships defined by department or job role and other potential organizational interactions. The GNN model trains on employees' attributes such as the job role, the performance ratings, satisfaction, and years at the company in addition to inferred relationships within teams and departments. With this, the model is able to capture effects of team dynamics and organizational structure on employee outcomes besides characteristics of individuals. Through the proposed framework, new hire personalization is to be enhanced with the identification of influencers, potential mentors, and optimal placements in teams. Results reflect GNN's ability to better predict the success of employees compared to NLP, as it analyzes a larger organizational network than the existing NLP, thereby introducing a more comprehensive and data-driven approach to HR decisionmaking. Its Scalability Solution offers companies an opportunity for optimizing onboarding, enhancing retention, and improving workforce performance by advanced machine learning techniques.