Effective machine learning, Meta-heuristic algorithms and multi-criteria decision making to minimizing human resource...

Area of Science:

• Human Resource Management
• Data Science
• Decision Support Systems

Background:

• Employee turnover presents significant challenges for organizations, impacting operational efficiency and costs.
• Effective human resource management requires understanding the multifaceted factors contributing to employee attrition.
• Current decision-making processes for managers are often hindered by the complexity of turnover drivers.

Purpose of the Study:

• To identify and rank the key factors influencing employee turnover.
• To evaluate the efficacy of various feature selection and decision-making algorithms in predicting turnover.
• To develop a data-driven decision support tool for human resource managers.

Main Methods:

• Feature selection algorithms: Recursive Feature Elimination (RFE) and Mutual Information (MI).
• Meta-heuristic algorithms: Gray Wolf Optimizer (GWO) and Genetic Algorithm (GA).
• Multi-Criteria Decision-Making (MCDM) technique: Best-Worst Method (BWM).
• Machine learning algorithms for performance evaluation and prediction accuracy assessment.

Main Results:

• Mutual Information (MI) algorithm identified factors that yielded superior performance in predicting employee turnover.
• The study confirmed the high potential for managerial decision-making errors without adequate support tools.
• Comparative analysis demonstrated the effectiveness of the implemented methods in uncovering significant turnover drivers.

Conclusions:

• The proposed approach, leveraging feature selection and MCDM, can serve as a valuable decision support tool for managers.
• Accurate identification of turnover factors enables organizations to develop targeted retention and optimization policies.
• Implementing data-driven insights can enhance strategic human resource management and reduce employee attrition.