集成算法在职业倦怠中的应用  

Application of ensemble algorithm in job burnout

作　　者：尹红[1] 周阳艳 顾满局 YIN Hong;ZHOU Yang-yan;GU Man-ju(Faculty of Mechanical and Electrical Engineering,Kunming University of Science and Technology,Kunming 650093,China)

机构地区：[1]昆明理工大学机电工程学院,昆明650093

出　　处：《信息技术》2023年第6期8-12,共5页Information Technology

基　　金：云南智能化自动化产业发展研究(YNDR2017G1C06)。

摘　　要：工作倦怠作为一种长期性的心理反应,虽然最初是从医疗和精神科的职业中探讨而来,但目前已普遍存在于各行各业中。尤其在COVID-19全球大流行的情况下,员工职业倦怠感更为严重。因此,文中使用四种集成算法对黑客地球平台发布的职业倦怠数据集进行预测,其中,随机森林MSE值为0.00401,梯度提升决策树MSE值为0.00383,XGBoost的MSE值为0.00381,Catboost的MSE值为0.00360,结果表明Catboost算法的预测效果较好。As a long-term psychological response,job burnout,although originally discussed from medical and psychiatric occupations,is now common in all walks of life.Especially in the context of the COVID-19 global pandemic,employee burnout is more serious.Therefore,four ensemble algorithms are used to predict the occupational burnout data set by the hacker earth platform,where the Random Forest’s MSE value is 0.00401,Gradient Boosting Decision Tree’s MSE value is 0.00383,XGBoost’s MSE value is 0.00381,Catboost’s MSE value is 0.00360,the results show that the prediction effect of the Catboost algorithm is better.

关 键 词：机器学习 职业倦怠 集成算法 预测 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]