Predictive Analytics for Employee Attrition Management Using Machine Learning Techniques

Employee turnover is a challenging situation for any organization because of high associated costs related to recruitment and training of new employees as well as losing organizational knowledge. This research aims to examine how machine learning can be used in predictive analytics in managing employee turnover through the use of the IBM HR Analytics data set. Five models including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and Gradient Boosting were tested systematically. It was revealed that ensemble models such as Random Forest have the highest predictive accuracy and AUC equal to 87.3% and 0.9348, respectively. Overtime, job satisfaction, monthly income, and tenure are found to be important factors affecting employee turnover. These results show that machine learning may change HR practices from reactive to proactive retention strategies based on data analysis.