Employee Turnover Prediction and Influencing Factors Based on Machine Learning

Employee turnover increases corporate recruitment and training costs. To foresee and effectively mitigate this risk, this article focuses on data processing using an employee turnover data set from Kaggle (a data science competition platform). Predictive modeling methods are employed to sequentially build four classification models for employee turnover prediction: Decision Tree, Support Vector Machine (SVM), Artificial Neural Network (ANN), and Random Forest. These models are used to analyze the key factors that influence employee turnover. The experimental results indicate that the Random Forest model outperforms the other three models in terms of metrics such as Accuracy, Precision, Recall, F1 Score, and AUC (Area Under Curve), demonstrating its superiority in predicting employee turnover. Therefore, this paper adopts the Random Forest model to calculate and rank the influence of various variables on employee turnover. Combined with histogram analysis, it is found that factors such as employee job satisfaction, the number of projects completed by employees, average monthly working hours, and years of service in the company have a higher impact on whether employees leave.This paper explores the factors influencing employee turnover from the perspective of machine learning algorithms, with the aim of providing timely warnings of employee turnover and serving as a reference for companies to enhance team stability.