Employee Turnover Prediction based on Machine Learning Model

Abstract

Research shows that high turnover rate will inevitably damage the sustainable and healthy development of the enterprise. Thanks to the rapid development of artificial intelligence technology, it is possible to build a model to predict employee turnover intension by analyzing employee turnover data. This study uses employee data of a company on the Kaggle platform, proposes an oversampling method for predicting employee turnover in view of data imbalance in the data set. Four models Gaussian NB, support vector machine for classification (SVC), K-Nearest Neighbor (KNN) and Gradient Boosting were established and trained to analyze the employee turnover features and predict the occurrence of employee turnover events.