Employee Turnover Prediction in Chinese Private Manufacturing: An Integrated Approach

DOI

10.2991/978-2-38476-456-3_22How to use a DOI?

Keywords

Employee Turnover; Machine Learning; Survival Analysis

Abstract

In recent years, employee turnover has become a significant concern for private manufacturing enterprises in China. It has led to an increase in human resource costs, such as those associated with recruitment, training, and new employee on-boarding. Additionally, the disruption of work processes and the obstruction of knowledge transfer among teams due to high turnover have negatively impacted operational continuity. Unfortunately, there is a lack of in-depth research specifically addressing the employee turnover issue within this industry. Drawing on 2,516 personnel records—1,566 former employees and 950 still on staff—from a Wenzhou manufacturer, we ran correlation checks, machine learning models, weight ranking, and survival-time analysis. The Random Forest classifier reached 95.6% accuracy, pinpointing work environment satisfaction as the strongest driver of turnover. This framework offers managers a clear path to lift retention and support steady growth.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Huijun Hao
AU  - Wei Chen
PY  - 2025
DA  - 2025/08/25
TI  - Employee Turnover Prediction in Chinese Private Manufacturing: An Integrated Approach
BT  - Proceedings of the 5th International Conference on New Computational Social Science (ICNCSS 2025)
PB  - Atlantis Press
SP  - 188
EP  - 196
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-456-3_22
DO  - 10.2991/978-2-38476-456-3_22
ID  - Hao2025
ER  -