Comparing the Performance of Machine Learning Algorithms for Predicting Employees’ Turnover

Employee turnover directly impacts companies ’ performance due to losing qualified staff and invested costs, so predicting the ability to turnover or staying will help companies reduce these effects. Therefore, this study aimed to predict turnover by building a model using selected machine learning algorithms based on secondary data of a big data company. The algorithms are Logistic Regression, K-Nearest Neighbors (KNN), Decision Tree, and Random Forest, which have been improved with different methods for better performance, like balancing data and important feature selection. The Random Forest was characterized by the best performance with 80.2% accuracy and 72.4% AUC, with city development index, experience, and university enrolment being the most important features. However, the performance of the Random Forest classifier can be enhanced by including other important features besides those highlighted by the model.