The Relationship-Oriented Turnover Prediction in Enterpreneurship Education for Enterprise Employees Based on CART Decision Tree Algorithm

This study explored the relationship between employee loneliness and turnover so as to ensure that enterprises can adjust personnel structure and management system in time. A classification and regression tree (CART) decision tree algorithm was proposed to predict employee turnover. First, the relationship between workplace loneliness and turnover intention was described. Then, the CART decision tree model was implemented, and a questionnaire survey (QS) was designed. The relationship between workplace loneliness and turnover intention was studied by correlation analysis and regression analysis. Second, the basic algorithm and principle of the CART decision tree were introduced, then the data set was determined according to the characteristic variables and target variables obtained from data preprocessing and feature selection. The data set was then randomly divided into the training set and test set with a ratio of 8:2.