Investigating Predicting Voluntary Resignation Program Participation with Machine Learning
Resumo
Context: The growing challenge in attracting employees to Voluntary Resignation Programs (VRP) lies in the need to balance the company’s cost control with the goal of increasing participation from the target audience. Problem: It is essential to ensure that the process occurs smoothly, reducing tension during the separation and fostering a more cooperative and responsible environment. Companies need to maximize attraction to VRP, minimize costs, and improve resource allocation. Solution: This article aims to construct a Machine Learning (ML) model to predict employee participation VRPs in an organizational context and to identify the key factors that influence employee participation in the program, identifying patterns and trends based on previous programs. IS Theory: This work is associated with the Theory of Computational Learning, which aims to understand the fundamental principles of learning and design better-automated methods. Method: This article constitutes a study of past data, aiming to identify patterns and develop trends related to employee participation through the utilization of ML algorithms. Summary of Results: The investigation into predicting VRP participation using ML revealed compelling correlations. The Bootstrap Aggregating with Logistic Regression model emerged as the most effective, demonstrating high F1-Score and Accuracy. Contributions and Impact in the IS area: The research significantly contributes to the IS field by showcasing ML’s application in predicting VRP participation, enriching our understanding of factors influencing employee decisions and highlights technology-driven solutions in workforce management. Insights from this investigation offer a valuable framework for future research, paving the way for predictive analytics integration in addressing complex HR challenges within the broader IS context.
