The amount of job turnover rate increased from 2018 to 2022 which had factors that lead to turnover such as job satisfaction, job burnout, years at work and ages. Many companies in Human Resources Management (HRM) have applied Machine Learning to collect data and predict whether the employee would be on the verge of expel or not. Also, they use these predictions to find the insight of employee turnover overrate and the way to prevent the problem. The researcher aims to develop models for predicting employee job turnover rates in a company by machine learning. The researcher aims to find factors that caused turnover and compare the predicted model performance. The model used in this research can be classified into two types of traditional models and Neural Network. The traditional models used in this research are Decision Tree, XG Boost, Random Forest, Logistic Regression, K-Nearest Neighbor (KNN) and Support Vector Machine (SVM). Neural Network that has been used is Artificial Neural Network (ANN). The result shows that the traditional models that had good performances are KNN and SVM which had Accuracy, Precision, Recall and F1 Score (0.85, 0.85), (0.81, 0.72), (0.85, 0.85), (0.79, 0.78) respectively.