Numerical Approximation Methods for Real-Time Employee Attrition  Classification: A Systematic Review of Algorithm Performance,  Computational Complexity, and Class-Imbalance Optimization

Abhimanyu Kumar

Numerical Approximation Methods for Real-Time Employee Attrition Classification: A Systematic Review of Algorithm Performance, Computational Complexity, and Class-Imbalance Optimization

Authors

Abhimanyu Kumar

Keywords:

employee attrition prediction, machine learning, ensemble methods, human resources analytics, Bi-LSTM, gradient boosting, random forest, feature selection, class imbalance, SMOTE, IBM Watson HR dataset, real-time prediction

Abstract

Employee turnover is one of the most serious business problems that modernorganisations face, and the cost of replacement for a lost employee can range from 50–200% of their annual salary (Allen et al., 2010). This synthesis is based on 16peer-reviewed studies and conference proceedings

References

Allen, D. G., Bryant, P. C., & Vardaman, J. M. (2010). Retaining talent: Replacing misconceptions with evidence-based strategies. Academy of Management Perspectives, 24(2), 48–64. https://doi.org/10.5465/amp.24.2.48

Downloads

Published

2023-04-20

How to Cite

Abhimanyu Kumar. (2023). Numerical Approximation Methods for Real-Time Employee Attrition Classification: A Systematic Review of Algorithm Performance, Computational Complexity, and Class-Imbalance Optimization. Journal of Computational Analysis and Applications (JoCAAA), 31(2), 822–840. Retrieved from https://eudoxuspress.com/index.php/pub/article/view/5655