An Improved Random Forest Algorithm for Predicting Employee Turnover

Mathematical Problems in Engineering - Tập 2019 Số 1 - 2019
Xiang Gao1, Junhao Wen2, Cheng Zhang1
1College of Computer Science, Chongqing University, Chongqing 400044, China
2College of Big Data & Software Engineering, Chongqing University, Chongqing 400044, China

Tóm tắt

Employee turnover is considered a major problem for many organizations and enterprises. The problem is critical because it affects not only the sustainability of work but also the continuity of enterprise planning and culture. Therefore, human resource departments are paying greater attention to employee turnover seeking to improve their understanding of the underlying reasons and main factors. To address this need, this study aims to enhance the ability to forecast employee turnover and introduce a new method based on an improved random forest algorithm. The proposed weighted quadratic random forest algorithm is applied to employee turnover data with high‐dimensional unbalanced characteristics. First, the random forest algorithm is used to order feature importance and reduce dimensions. Second, the selected features are used with the random forest algorithm and the F‐measure values are calculated for each decision tree as weights to build the prediction model for employee turnover. In the area of employee turnover forecasting, compared with the random forest, C4.5, Logistic, BP, and other algorithms, the proposed algorithm shows significant improvement in terms of various performance indicators, specifically recall and F‐measure. In the experiment using the employee dataset of a branch of a communications company in China, the key factors influencing employee turnover were identified as monthly income, overtime, age, distance from home, years at the company, and percent of salary increase. Among them, monthly income and overtime were the two most important factors. The study offers a new analytic method that can help human resource departments predict employee turnover more accurately and its experimental results provide further insights to reduce employee turnover intention.

Từ khóa


Tài liệu tham khảo

10.1016/0278-4319(92)90007-I

10.1080/00909880701799790

10.1016/j.chb.2017.02.017

HongW. C. PaiP.-F. Huang-Y. andYang-L. Application of support vector machines in predicting employee turnover based on job performance Proceedings of the International Conference on Advances in Natural Computation 2005 Berlin Germany Springer 668–674.

Kao H.-W., 2012, Applying decision tree to predict nursing turnover-a case study in a public hospital, The Journal of Taiwan Association for Medical Informatics, 21, 15

ChienH.-J. Application of the two-stage cluster analysis on employee voluntary turnover intention [M.S. thesis] 2007 Yuan Ze University.

WuC.-T. Using the decision tree approach to forecast contractor turn over trend – a case study of wafer foundry [M.S. thesis] 2008 National Cheng Kung University.

10.2307/3069391

10.1037/mil0000055

10.1007/s11628-016-0330-5

10.1016/j.apnr.2017.11.027

Tran H., 2016, The impact of pay satisfaction and school achievement on high school principals′ turnover intentions, Educational Management Administration and Leadership, 45, 279

10.1023/A:1010933404324

10.1016/j.neucom.2017.05.094

10.1109/ACCESS.2018.2812141

10.1007/s10489-017-0976-2

10.1016/j.saa.2017.10.052

10.1002/ima.22255

10.1016/j.patcog.2018.01.025

10.1016/j.eswa.2017.12.029

10.1007/s10994-017-5642-8

10.1016/j.bdr.2017.07.003

10.1109/ACCESS.2018.2789428

10.1007/BF00993309

Thông tin
Thông tin xuất bản

Mathematical Problems in Engineering

Tập 2019 Số 1

Thông tin tác giả