Prediction of Employee Turnover Intention in Enterprises Based on Machine Learning

This study compares the performance of logistic regression, gradient boosting and random forest models in employee turnover intention prediction. It is found that the gradient boosting model has the best prediction performance, which can accurately capture the complex relationship of data, and the prediction accuracy is better than other models. The feature importance analysis of the model reveals that monthly income, age, years at company, performance rating, and overtime status are the pivotal factors influencing employee turnover intention. The research not only clarifies the key driving factors of employee turnover, but also provides a scientific basis for enterprises to construct hierarchical classification retention strategies and optimize human resource management.