Document Type : Research Paper
Authors
1 Student
2 Professor of Department of Management, Ferdowsi University of Mashhad, Mashhad, Iran
3 Associate professor of Department of Management, Ferdowsi University of Mashhad, Mashhad, Iran
4 Associate professor of Department of Medical Informatics, Mashhad University of Medical Sciences, Mashhad, Iran
Abstract
Migration of human resources in the health sector not only reduces the quality of healthcare services but also imposes detrimental social and economic consequences on developing countries such as Iran. Therefore, accurately modeling the decision-making behavior of this workforce requires advanced analytical approaches to capture complexities and social interactions. This study aimed to design and validate a data driven agent-based model to simulate migration behavior among healthcare professionals in Iran. Secondary data were employed from the 2023 survey entitled “National Survey on Elite Migration and Factors Influencing the Outflow of Human Capital in the Health Sector” conducted by the Iranian Migration Observatory using a standardized questionnaire. The research adopted a hybrid framework in which 384 balanced samples were used for training, and the Random Forest machine learning algorithm served as the behavioral meta model of agents to directly extract nonlinear decision-making rules from microdata. The model output, representing the migration probability of each agent, was then integrated into the agent-based simulation, where comparison with an optimal decision threshold determined the final migration or non-migration action. Results indicated that the data driven agent model significantly outperformed the theory driven agent model based on logistic regression in predicting migration intentions. Furthermore, analyses confirmed that key variables such as age, work experience, and social network effects played nonlinear and essential roles in shaping final decisions.
Keywords
Main Subjects
)