基于改进XGBoost的企业员工离职预测模型  

Employee turnover prediction model based on improved XGBoost

作　　者：王瑞 尹红[1] 强冰冰 WANG Rui;YIN Hong;QIANG Bing-bing(Faculty of Mechanical and Electrical Engineering,Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学机电工程学院,昆明650500

出　　处：《信息技术》2021年第8期12-15,20,共5页Information Technology

基　　金：云南省人民政府发展研究课题项目(YNDR2017G1-C06)。

摘　　要：建立企业员工离职预测模型找出有离职倾向的员工,可以提前采取有针对性的措施,降低人才流失对企业发展造成的影响。文中选取IBM Watson Analytics平台发布的数据集,建立基于改进XGBoost算法的模型并与未改进前的模型进行比较研究。结果表明,改进后的模型在召回率以及AUC值指标上提高了100%和8%。In order to avoid the harm of brain drain caused to the development of enterprise,we could take targeted measures in advance to establish the prediction model of employee turnover to find out the employee who has turnover intention.This paper selects the data set published by IBM Watson analytics platform,based on which establishes the model based on the improved xgboost algorithm,and compares it with the model before improvement.The results show that the recall rate and AUC value of the improved model are increased by 100%and 8%.

关 键 词：机器学习 员工离职预测 XGBoost算法 不平衡数据 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]