Nowadays, Employee turnover is a serious issue in organizations. It affects the time,rnproductivity, and stability of the given organizations. Employees are very important that helpsrnthe organization get success and gain revenue. So, Organizations need to know the key issuesrnthat the reason for employee turnover. Prediction models are highly associated with humanrnresource management to identify the employee turnover patterns from employee previouslyrnrecorded data. The objective of this research is to design a model and predicting staff turnoverrnusing a machine learning approach in the Ethiopian Federal court organization. For predictionrnthree classification models namely, random forest, logistic regression and gradient boosting treernwere used. The total datasets from the three federal court organizations were 3610 both activernand terminated.For evaluate the prediction classification models the researcher was usernconfusion matrix, recall, precision and roc-curve to measure the performance of the classifiers.rnAfter evaluation, from the three classification models the finding shows that the bestrnclassification model is gradient boosting tree with an accuracy of 87.5%. Additionally, from thernstudy it is found that the factors responsible for employee turnover are:-experience, salary, agernand employeeâ€™s number of year service are the most significant factors. The factors martial andrngender were low predictor variables on employee turnover in the federal court organization.Thernstudy concludes that the most reliable and accurate classification model to predict employeernturnover isan ensemble â€“ based learning technique gradient boosting tree that was found as thernmost suitable classifier for building the predictive model.