Dr. Mutaz Abua Sara and Mr. Sameh Taqatqah published a new paper titled "A Predictive Approach and Recommendation System for Employee Turnover Using Machine Learning Algorithms"

Abstract

This research focuses on predicting employee turnover et al.-Istiqlal University using machine learning algorithms. The study employs the CRISP methodology, utilizing a dataset from the university’s human resources department. Key phases include data preprocessing, feature selection, and the application of classification models like Random Forest, Logistic Regression, and Support Vector Machines. Random Forest emerges as the most effective model. The study emphasizes the importance of real-world data, comprehensive feature selection, and model interpretability. The deployment phase introduces Local Interpretable Model-Agnostic Explanations (LIME) for enhanced interpretability, providing insights into individual predictions and the impact of various factors on turnover. Continuous monitoring and refinement based on real-world feedback are recommended for sustained effectiveness in addressing employee turnover challenges.

How to cite

Taqatqa, S., Taqatqa, R., Sara, M. R. A., Samhan, A. A. A., & Kanan, M. (2025). A Predictive Approach and Recommendation System for Employee Turnover Using Machine Learning Algorithms. In Intelligence-Driven Circular Economy: Regeneration Towards Sustainability and Social Responsibility—Volume 2 (pp. 429-441). Cham: Springer Nature Switzerland.

View at publisher

https://link.springer.com/chapter/10.1007/978-3-031-74220-0_33