期刊
ENTERPRISE INFORMATION SYSTEMS
卷 17, 期 8, 页码 -出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/17517575.2022.2130013
关键词
The turnover decision; job satisfaction; turnover risk prediction; random forest; the Internet sector
This paper proposes the importance of work-life balance, compensation, career opportunity, and culture and management style in improving job satisfaction. A turnover risk prediction model based on the random forest algorithm is constructed to understand the characteristics and identify risks of turnover. Empirical analysis using a sample of 17,724 online reviews from Glassdoor confirms the positive effects of antecedents, with job satisfaction as a mediator and the unemployment rate as a moderator. Finally, job satisfaction is identified as the most crucial feature for predicting turnover.
This paper proposes that high value on the work-life balance, compensation, career opportunity and fitness of culture and management style would improve job satisfaction. A turnover risk prediction model based on the random forest is constructed to understand the turnover risk feature and identify risk. Using a sample of 17,724 online reviews of employees from Glassdoor, the positive effect of antecedents, the job satisfaction variable as a mediator, and the unemployment rate variable as a moderator is verified. Finally, job satisfaction is identified as the most important feature for predicting turnover based on the random forest algorithm.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据