Turnover Prediction in Human Resource Management via Deep Variational Information Bottleneck

Hengxiaoyuan  Wang

doi:10.6180/jase.202504_28(4).0003

Turnover Prediction in Human Resource Management via Deep Variational Information Bottleneck

Computer Science and Information Engineering

Turnover prediction of employees has become a key focus for human resource specialists, as it is broadly viewed as a vital measure of an organization’s competitive edge. To this end, a new deep variational information bottleneck network based turnover prediction method is proposed for human resource management (TP-VIB). Specifically, The information bottleneck is utilized to model the turnover prediction task, and then variational inference method is used to obtain lower bound of the IB for optimizing representation learning and pattern mining networks within the deep framework. Furthermore, a entropy regularization term is designed to balance positive and negative class imbalances in employee turnover datasets. Finally, the experiment results demonstrate that TP-VIB sets a new baseline method for employee turnover prediction tasks

Hengxiaoyuan WangThis email address is being protected from spambots. You need JavaScript enabled to view it.

Dalian University Of Finance And Economics, Dalian, 116620, China

Received: April 8, 2024
Accepted: May 7, 2024
Publication Date: May 25, 2024

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202504_28(4).0003

Turnover prediction of employees has become a key focus for human resource specialists, as it is broadly viewed as a vital measure of an organization’s competitive edge. To this end, a new deep variational information bottleneck network based turnover prediction method is proposed for human resource management (TP-VIB). Specifically, The information bottleneck is utilized to model the turnover prediction task, and then variational inference method is used to obtain lower bound of the IB for optimizing representation learning and pattern mining networks within the deep framework. Furthermore, a entropy regularization term is designed to balance positive and negative class imbalances in employee turnover datasets. Finally, the experiment results demonstrate that TP-VIB sets a new baseline method for employee turnover prediction tasks.

Keywords: Turnover prediction; information bottleneck; deep framework

[1] R. J. Stone, A. Cox, M. Gavin, and J. Carpini. Human resource management. 2024.
[2] P. Li, J. Gao, J. Zhang, S. Jin, and Z. Chen, (2022) “Deep Reinforcement Clustering" IEEE Transactions on Multimedia: DOI: 10.1109/TMM.2022.3233249.
[3] S. Yuan, B. Kroon, and A. Kramer, (2024) “Building prediction models with grouped data: A case study on the prediction of turnover intention" Human Resource Management Journal 34(1): 20–38.
[4] J. Gao, M. Liu, P. Li, J. Zhang, and Z. Chen, (2023) “Deep Multiview Adaptive Clustering With Semantic In variance" IEEE Transactions on Neural Networks and Learning Systems: DOI: 10.1109/TNNLS.2023.3265699.
[5] P. Li, Z. Chen, L. T. Yang, J. Gao, Q. Zhang, and M. J. Deen, (2018) “An incremental deep convolutional compu tation model for feature learning on industrial big data" IEEE Transactions on Industrial Informatics 15(3): 1341–1349. DOI: 10.1109/TII.2018.2871084.
[6] C. S. Lim, E. F. Malik, K. W. Khaw, A. Alnoor, X. Chew, Z. L. Chong, and M. Al Akasheh, (2024) “Hy brid GA–DeepAutoencoder–KNN Model for Employee Turnover Prediction" Statistics, Optimization & Infor mation Computing 12(1): 75–90. DOI: 10.19139/soic-2310-5070-1799.
[7] J. Park, Y. Feng, and S.-P. Jeong, (2024) “Developing an advanced prediction model for new employee turnover intention utilizing machine learning techniques" Scien tific Reports 14(1): 1221. DOI: 10.1038/s41598-02350593-4.
[8] J. Park, Y. Feng, and S.-P. Jeong, (2024) “Developing an advanced prediction model for new employee turnover intention utilizing machine learning techniques" Scien tific Reports 14(1): 1221. DOI: 10.1038/s41598-023-50593-4.
[9] Q.Zhu,J.Shang, X. Cai, L. Jiang, F. Liu, and B. Qiang. “CoxRF: Employee turnover prediction based on sur vival analysis”. In: IEEE SmartWorld, Ubiquitous Intel ligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Inno vation. 2019, 1123–1130.
[10] Z.Jin, J. Shang, Q. Zhu, C. Ling, W. Xie, and B. Qiang. “RFRSF: Employee turnover prediction based on ran domforests and survival analysis”. In: Web Informa tion Systems Engineering–WISE 2020: 21st International Conference, Amsterdam, The Netherlands, October 20–24, 2020, Proceedings, Part II 21. 2020, 503–515.
[11] S. Abdelsalam, P. A. Agius, R. Sacks-Davis, A. Rox burgh, M. Livingston, L. Maher, M. Hickman, and P. Dietze, (2024) “Characteristics of attrition within the SuperMIX cohort of people who inject drugs: A multiple event discrete-time survival analysis": DOI: 10.21203/rs.3.rs-3922479/v1.
[12] I. G. Kang, B. Croft, and B. A. Bichelmeyer, (2021) “Predictors of turnover intention in US federal govern ment workforce: Machine learning evidence that perceived comprehensive HR practices predict turnover intention" Public Personnel Management 50(4): 538–558. DOI: 10.1177/0091026020977562.
[13] V. Nagadevara and V. Srinivasan, (2008) “Early pre diction of employee attrition in software companies application of data mining techniques" Research and Practice in Human Resource Management 16: 2020 2032.
[14] N. El-Rayes, M. Fang, M. Smith, and S. M. Taylor, (2020) “Predicting employee attrition using tree-based models" International Journal of Organizational Analysis 28(6): 1273–1291. DOI: 10.1108/IJOA-10-2019-1903.
[15] F. Alsubaie and M. Aldoukhi, (2024) “Using machine learning algorithms with improved accuracy to analyze and predict employee attrition" Decision Science Let ters 13(1): 1–18. DOI: 10.5267/j.dsl.2023.12.006.
[16] X. Cai, J. Shang, Z. Jin, F. Liu, B. Qiang, W. Xie, and L. Zhao,(2020)“DBGE:employeeturnoverpredictionbased on dynamic bipartite graph embedding" IEEE Access 8: 10390–10402. DOI: 10.1109/ACCESS.2020.2965544.
[17] J. Park, S. Kwon, and S.-P. Jeong, (2023) “A study on improving turnover intention forecasting by solving imbalanced data problems: focusing on SMOTE and gen erative adversarial networks" Journal of Big Data 10(1): 36.
[18] Y. Liu, L. Zhang, L. Nie, Y. Yan, and D. Rosenblum. “Fortune teller: predicting your career path”. In: Pro ceedings of the AAAI conference on artificial intelligence. 30. 1. 2016.
[19] F. Guerranti and G. M. Dimitri, (2022) “A comparison of machine learning approaches for predicting employee attrition" Applied Sciences 13(1): 267. DOI: 10.3390/app13010267.
[20] J. Gao, M. Liu, P. Li, A. A. Laghari, A. R. Javed, N. Victor, and T. R. Gadekallu, (2023) “Deep Incomplete Multi-View Clustering Via Information Bottleneck for Pattern Mining of Data in Extreme-Environment IoT" IEEE Internet of Things Journal: DOI: 10.1109/JIOT.2023.3325272.
[21] B.Perozzi, R. Al-Rfou, and S. Skiena. “Deepwalk: On line learning of social representations”. In: Proceed ings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 2014, 701–710. DOI: 10.1145/2623330.2623732.
[22] Y. Chang, E. Tanin, X. Cao, and J. Qi. “Spatial Structure-Aware Road Network Embedding via Graph Contrastive Learning.” In: EDBT. 2023, 144-156