Machine Learning Applications in Predicting Employee Turnover: A Systematic Review
DOI:
https://doi.org/10.70112/ajeat-2025.14.2.4329Keywords:
Employee Turnover, Machine Learning, Predictive Analytics, Explainable AI (XAI), Human Resources (HR) AnalyticsAbstract
Employee turnover remains a critical and costly challenge for organizations globally, necessitating advanced predictive tools beyond traditional statistical methods. This systematic literature review (SLR) investigates the application of machine learning (ML) models in predicting employee attrition, synthesizing findings from 42 peer-reviewed articles and conference proceedings published between January 2020 and September 2025. Following the PRISMA 2020 guidelines, the review analyzes the algorithmic landscape, predictive feature importance, and methodological challenges in this domain. Results indicate that ensemble methods, particularly Random Forest and XGBoost, consistently outperform baseline models such as Logistic Regression, achieving typical accuracies between 85% and 94%. A consistent set of features-including low job satisfaction, excessive overtime workload, and below-market compensation-emerged as the strongest predictors of attrition risk. Furthermore, the review highlights the critical role of Explainable AI (XAI) techniques, such as SHAP and LIME, in translating complex model predictions into actionable insights for Human Resources (HR) professionals, thereby addressing concerns about model opacity and fostering stakeholder trust. Methodological challenges, including class imbalance and the risk of algorithmic bias, are discussed alongside common mitigation strategies. This review concludes by outlining emerging trends, such as hybrid models and prescriptive analytics, providing a comprehensive reference for researchers and practitioners seeking to implement responsible and effective ML-driven workforce analytics.
References
[1] Opportunities and risks of artificial intelligence in recruitment and selection,” Int. J. Organizational Anal., vol. 30, no. 6, pp. 1771–1782, 2021, doi: 10.1108/IJOA-07-2020-2291.
[2] “Human resources analytics: Leveraging human resources for enhancing business performance,” Compens. Benefits Rev., vol. 55, no. 1, pp. 31–45, 2022, doi: 10.1177/08863687221131730.
[3] “Bridging the gap: Why, how and when HR analytics can impact organizational performance,” Manag. Decision, vol. 60, no. 13, pp. 25–47, 2022, doi: 10.1108/MD-12-2020-1581.
[4] “Examining the determinants of successful adoption of data analytics in human resource management – A framework for implications,” J. Bus. Res., vol. 131, pp. 311–326, 2021, doi: 10.1016/j.jbusres.2021.03.054.
[5] “Uplift modeling vs conventional predictive model: A reliable machine learning model to solve employee turnover,” Int. J. Artif. Intell. Res., vol. 5, no. 1, 2021, doi: 10.29099/ijair.v4i2.169.
[6] “AI-driven HR analytics: Unleashing the power of HR data management,” J. Technol. Syst., vol. 5, no. 2, pp. 15–26, 2023, doi: 10.47941/jts.1513.
[7] “Tackling the HR digitalization challenge: Key factors and barriers to HR analytics adoption,” Competitiveness Rev., vol. 31, no. 1, pp. 162–187, 2020, doi: 10.1108/CR-12-2019-0163.
[8] M. Al Akasheh et al., “A decade of research on machine learning techniques for employee turnover prediction: A systematic review,” Expert Syst. Appl., vol. 220, p. 119128, 2024, doi: 10.1016/j.eswa.2023.119128.
[9] “Predictive analytics in business analytics: Decision tree,” Adv. Decision Sci., vol. 26, no. 1, pp. 1–30, 2022, doi: 10.47654/v26y2022i1p1-30.
[10] “The challenges of algorithm-based HR decision-making for personal integrity,” in Proc. Int. Conf. Privacy Integrity, pp. 71–86, 2022, doi: 10.1007/978-3-031-18794-0_5.
[11] “Leveraging HR analytics for strategic decision making: Opportunities and challenges,” Int. J. Manag. Entrepreneurship Res., vol. 6, no. 4, pp. 1304–1325, 2024, doi: 10.51594/ijmer.v6i4.1060.
[12] H. Talebi, “Machine learning approaches for predicting employee turnover,” Eng. Rep., vol. 7, no. 3, 2025, doi: 10.1002/eng2.70298.
[13] S. M. Varkiani et al., “Predicting employee attrition and explaining its determinants,” Expert Syst. Appl., vol. 185, p. 115992, 2025, doi: 10.1016/j.eswa.2025.115992.
[14] “Enhancing employee retention: Predicting attrition using machine learning models,” J. Appl. Bus. Econ., vol. 27, no. 3, 2025.
[15] “Prediction of employee turnover with imbalance dataset using machine learning methods,” Int. J. Adv. Natural Sci. Eng. Res., vol. 7, no. 9, pp. 12–16, 2023.
[16] “Enhancing efficiency of employee attrition prediction using machine learning and ensemble techniques,” M.S. thesis, Nat. College Ireland, Dublin, Ireland, 2024.
[17] “Predicting employee turnover in IT & ITeS industry using machine learning algorithms,” in Proc. IEEE Int. Conf. Computational Intell. Data Sci. (ICCIDS), pp. 1–6, 2020, doi: 10.1109/ICCIDS49852.2020.9243552.
[18] “Predicting employee attrition using machine learning techniques,” Acta Informatica Pragensia, vol. 14, no. 1, pp. 112–127, 2025, doi: 10.18267/j.aip.255.
[19] “Investigating employee attrition using machine learning and causal inference techniques,” World J. Adv. Res. Rev., 2025.
[20] Z. Li et al., “Explainable machine learning and graph neural network approaches for employee attrition,” in Proc. ACM Conf. Fairness Accountab. Transpar., pp. 354–364, 2024.
[21] “Integrating artificial intelligence into a talent management model to increase work engagement and performance,” Front. Psychol., vol. 13, 2022, doi: 10.3389/fpsyg.2022.1014434.
[22] “Explainable AI: A review of machine learning interpretability methods,” Entropy, vol. 23, no. 1, p. 18, 2020, doi: 10.3390/e23010018.
[23] “XAI for churn prediction in B2B models: A use case in an enterprise software company,” Mathematics, vol. 10, no. 20, p. 3896, 2022, doi: 10.3390/math10203896.
[24] “Interpretable gradient boosted modeling of employee attrition using SHAP,” Int. J. Anal. Appl., vol. 23, 2025.
[25] “An end-to-end framework for predicting employee attrition with explainable AI,” Int. J. Sci. Res. Eng. Dev., vol. 8, no. 4, pp. 1786–1795, 2025.
[26] “IBM HR analytics: Employee turnover analysis,” Kaggle, 2025.
[27] “Featuring machine learning models to evaluate employee attrition prediction,” Int. Res. J. Modernization Sci. Technol., vol. 7, 2025.
[28] “Employee attrition prediction based on machine learning,” in Proc. Atlantis Press Conf., 2025.
[29] S. Fukui et al., “Applying machine learning to human resources data to predict employee turnover,” Hum. Serv. Organ. Manag. Leadership Governance, vol. 47, no. 3, pp. 207–217, 2023.
[30] “Empowering human resource functions with data-driven decision-making in start-ups: A narrative inquiry approach,” Int. J. Organizational Anal., vol. 31, no. 4, pp. 945–958, 2021, doi: 10.1108/IJOA-08-2021-2888.
[31] “Artificial intelligence and public sector human resource management in South Africa: Opportunities, challenges and prospects,” SA J. Hum. Resour. Manag., vol. 20, 2022, doi: 10.4102/sajhrm. v20i0.1972.
[32] “Strategic HRM in the logistics and shipping sector: Challenges and opportunities,” Int. J. Sci. Res. Archive, vol. 11, no. 1, pp. 2000–2011, 2024, doi: 10.30574/ijsra.2024.11.1.0269.
[33] “Modeling challenges to implement HR analytics in IT sector using ISM,” J. Life Econ., vol. 11, no. 2, pp. 49–60, 2024, doi: 10.15637/jlecon.2407.
[34] “Adoption of HR analytics to enhance employee retention in the workplace: A review,” Hum. Resour. Manag. Serv., vol. 6, no. 3, p. 3481, 2024, doi: 10.18282/hrms. v6i3.3481.
[35] “The integration of HR analytics and decision making,” Productivity, vol. 1, no. 1, pp. 182–189, 2024, doi: 10.62207/aj4nj061.
[36] “PRISMA 2020 statement: An updated guideline for reporting systematic reviews,” BMJ, vol. 372, 2021.
[37] “Navigating the complexity of HR analytics: A conceptual framework for effective implementation and ethical practice,” Int. J. Multidisciplinary Res., vol. 6, no. 2, 2024, doi: 10.36948/ijfmr. 2024.v06i02.15557.
[38] “Analyzing employee attrition using explainable AI for strategic HR decision-making,” Mathematics, vol. 11, no. 22, p. 4677, 2023, doi: 10.3390/math11224677.
[39] “The HR analytics cycle: A seven-step process for building evidence-based and ethical HR analytics capabilities,” J. Work-Appl. Manag., vol. 13, no. 1, pp. 51–68, 2020, doi: 10.1108/JWAM-03-2020-0020.
[40] “AI-driven talent analytics for strategic HR decision-making in the United States of America: A review,” Int. J. Manag. Entrepreneurship Res., vol. 4, no. 12, pp. 607–622, 2023, doi: 10.51594/ijmer. v4i12.674.
[41] “The future of work: Implications of artificial intelligence on HR practices,” TJJPT, vol. 44, no. 3, pp. 1711–1724, 2023, doi: 10.52783/tjjpt. v44.i3.562.
[42] “Enhancing human resource management through advanced decision-making strategies: Harnessing the power of artificial intelligence,” Migration Lett., vol. 21, no. S8, pp. 881–889, 2024, doi: 10.59670/ml.v21is8.9488.
[43] “Human resource analytics: A review and bibliometric analysis,” Personnel Rev., vol. 51, no. 1, pp. 251–283, 2021, doi: 10.1108/PR-04-2020-0247.
[44] “Challenges and opportunities of big data analytics for human resource management in mining and metal industries,” J. Mines Metals Fuels, pp. 1747–1753, 2023, doi: 10.18311/jmmf/2023/35858.
[45] “Strategic role of artificial intelligence (AI) on human resource management (HR) employee performance evaluation function,” Int. J. Entrepreneurship Bus. Innovation, vol. 7, no. 2, pp. 269–282, 2024, doi: 10.52589/ijebi-het5styk.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Centre for Research and Innovation
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
