Predictive Modeling for B.Sc. Nursing Placement Using Machine Learning Algorithms

The demand for well-trained nursing professionals is ever-increasing, necessitating efficient placement processes post-graduation. This study explores the application of machine learning (ML) algorithms to predict B.Sc. Nursing placement outcomes, aiming to optimize workforce management and graduate placement efficiency. Traditional placement methods often suffer from subjectivity and inefficiency. Leveraging historical placement data and relevant features, ML algorithms discern patterns to forecast individual placement likelihood accurately. Various ML techniques including logistic regression, decision trees, support vector machines, and ensemble methods are employed and evaluated for their predictive efficacy. The CN2 rule inducer model emerges as the top-performing model, demonstrating superior discriminatory ability and accuracy. These findings offer significant implications for nursing education institutions and healthcare organizations, facilitating better alignment of education with workforce demands. However, the study also emphasizes the importance of balancing model performance with interpretability. Further research and implementation efforts are warranted to refine predictive modeling approaches and seamlessly integrate them into nursing education and workforce management practices, ultimately contributing to the advancement of nursing practice and patient care delivery.