Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68254
Volume:
10 |
10 |
Oct 2026
Pages:
1-10
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Science And Engineering
Prof. Ram Meghe Institute of Technology and Research Badnera - Amravati
Computer Science And Engineering
Prof. Ram Meghe Institute of Technology and Research Badnera - Amravati
Computer Science And Engineering
Prof. Ram Meghe Institute of Technology and Research Badnera - Amravati
Computer Science And Engineering
Prof. Ram Meghe Institute of Technology and Research Badnera - Amravati
Computer Science And Engineering
Prof. Ram Meghe Institute of Technology and Research Badnera - Amravati
Computer Science And Engineering
Prof. Ram Meghe Institute of Technology and Research Badnera - Amravati
Employee attrition prediction is a well-studied application of machine learning (ML), and the public IBM HR Analytics Employee Attrition and Performance dataset has become its most common benchmark. Most studies, however, stop at classification performance and leave unanswered what an organisation should do with a risk score. This review examines three connected areas: (i) ML approaches to attrition prediction on the IBM dataset, including gradient boosting, ensemble methods and deep learning; (ii) evaluation practice, including class imbalance, resampling order, and precision-recall analysis; and (iii) the emerging use of workflow automation platforms such as n8n, together with calendar services, to turn predictions into HR follow-up actions under human review. We also discuss explainability, fairness, privacy and human oversight, and we use a recent prototype that links a gradient boosting classifier to a Google Calendar scheduling workflow as an illustrative case. The literature we examined shows that results across studies are not directly comparable, that evaluation of the prediction-to-action step is largely missing in the sources examined, and that responsible-use safeguards need explicit testing. We close with a research agenda. The review is non-systematic and covers a limited set of sources; its conclusions describe those sources and should not be read as a claim about all existing work.
KEYWORDS
The attrition literature we examined concentrates on prediction accuracy on a single fictional benchmark, with conclusions about the best model that depend heavily on protocol. Practitioner work has started to connect predictions to automated actions, but without reported evaluation. We argue that attrition systems should be assessed as two linked components, a classifier evaluated with leakage-free, imbalance-aware and uncertainty-aware metrics, and a workflow evaluated with explicit reliability metrics, wrapped in human review and privacy safeguards. Every score should be treated as a risk indicator and not as evidence that someone intends to resign. The review is limited by its non-systematic search and its small set of sources, and its conclusions should be read accordingly.
[1] A. Raza, K. Munir, M. Almutairi, F. Younas, and M. M. S. Fareed, "Predicting employee attrition using machine learning approaches," Appl. Sci., vol. 12, no. 13, Art. no. 6424, 2022, doi: 10.3390/app12136424. [2] W. Li, "A transformer-based deep learning framework to predict employee attrition," PeerJ Comput. Sci., 2023, doi: 10.7717/peerj-cs.1570. [3] M. Nandal, V. Grover, D. Sahu, and M. Dogra, "Employee attrition: Analysis of data-driven models," EAI Endorsed Trans. Internet Things, vol. 10, no. 1, 2024, doi: 10.4108/eetiot.4762. [4] "IBM HR analytics employee attrition & performance," Kaggle dataset (contributor: pavansubhasht). [Online]. Available: https://www.kaggle.com/datasets/pavansubhasht/ibm-hr-analytics-attrition-dataset (accessed Oct. 11, 2026). [5] J. H. Friedman, "Greedy function approximation: A gradient boosting machine," Ann. Statist., vol. 29, no. 5, pp. 1189-1232, 2001, doi: 10.1214/aos/1013203451. [6] F. Pedregosa et al., "Scikit-learn: Machine learning in Python,"J. Mach. Learn. Res., vol. 12, pp. 2825-2830, 2011. [7] T. Saito and M. Rehmsmeier, "The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets," PLoS ONE, vol. 10, no. 3, Art. no. e0118432, 2015, doi: 10.1371/journal.pone.0118432. [8] S. M. Lundberg and S.-I. Lee, "A unified approach to interpreting model predictions," in Advances in Neural Information Processing Systems, vol. 30, 2017, pp. 4765-4774. [9] N. Mehrabi, F. Morstatter, N. Saxena, K. Lerman, and A. Galstyan, "A survey on bias and fairness in machine learning," ACM Comput. Surv., vol. 54, no. 6, pp. 1-35, 2021, doi: 10.1145/3457607. [10] n8n, "Google Calendar node," n8n Documentation. [Online]. Available: https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.googlecalendar/ (accessed Oct. 11, 2026).
Publication Date
10/24/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
3
Total views since publication
PDF Downloads
7
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...