Predictive Modeling of Employee Attrition Using Tree-Based Machine Learning Classifiers

Employee attrition poses considerable challenges for organizations by affecting productivity and increasing recruitment costs. This study employs tree-based machine learning classifiers to predict employee attrition, aiming to improve decision-making in human resource management. The J48 decision tree was utilized for feature selection, and several classifiers, including Hoeffding Tree, Rep Tree, J48, Random Forest, LMT, and Random Tree, were evaluated. Among these, the Random Forest classifier achieved the highest accuracy of 87.07%, demonstrating its effectiveness in modeling complex attrition patterns. The study offers insights into the application of machine learning for predicting employee attrition and provides a framework for organizations to maintain workforce stability. Future research could incorporate additional data sources and advanced methods to enhance prediction accuracy.