ISSN2320-2882
Impact Factor9.17
UGC ParametersAligned
Low Cost₹1501 / $59
CrossRefDOI
ESTD2013
Peer ReviewTransparent
AccessOpen
Submission: Always Open
Paper Title
Explainable Machine Learning Framework for Predicting Employee Attrition and Layoffs in HR Management
Authors
Mrs. Sowjanya Balaga , Reddymalla Bhavani , Sri Vardhan Jandhyala , H Srikanth
Keywords
Employee Attrition, Layoff Prediction, Machine Learning, Ensemble Learning, Explainable AI (XAI), SHAP, LIME, Human Resource Analytics, Feature Engineering, SMOTE, Workforce Management. INTRODUCTION
Abstract
This study presents a clear machine learning approach to identify employees who might leave an organization or face layoffs. The main goal is to help human resource teams make informed decisions based on data. The model combines predictions of voluntary attrition and involuntary layoffs into one framework, analyzing various employee-related attributes like job performance, salary, and organizational factors. Before applying machine learning methods, the data undergoes careful preparation, including cleaning, transformation, and feature selection. Since real-world HR data often has imbalances, techniques such as SMOTE are used to ensure better model learning. The prediction system uses ensemble algorithms, including Random Forest and XGBoost, which help enhance reliability and performance. To make the system more transparent and trustworthy, it includes explainability methods like SHAP and LIME. These methods highlight the key factors behind each prediction, allowing HR professionals to understand the reasons for employee risk levels instead of relying on black-box outputs. The proposed system also features a user-friendly dashboard that displays predictions, risk scores, and key contributing factors in a visual format. This helps organizations take timely actions, such as improving employee engagement or planning workforce changes more effectively. Overall, the framework aims to balance predictive performance with clarity, helping organizations lower turnover costs and improve workforce stability.
Full Paper, Downloads & Preview
How To Cite
Choose the style your journal or department asks for, then copy it. Every version below is generated from this paper's own record.
IJCRT — journal style
"Explainable Machine Learning Framework for Predicting Employee Attrition and Layoffs in HR Management", IJCRT - International Journal of Creative Research Thoughts (www.ijcrt.org), ISSN:2320-2882, Vol.14, Issue 3, page no.i266-i271, March 2026, Available :https://ijcrt.org/papers/IJCRT2603999.pdf
APA — 7th edition
Balaga, S., Bhavani, R., Jandhyala, V., & Srikanth, H. (2026). Explainable Machine Learning Framework for Predicting Employee Attrition and Layoffs in HR Management. International Journal of Creative Research Thoughts, 14(3), i266-i271. https://doi.org/10.56975/ijcrt.v14i3.304033
MLA — 9th edition
Balaga, Sowjanya, et al. "Explainable Machine Learning Framework for Predicting Employee Attrition and Layoffs in HR Management." International Journal of Creative Research Thoughts, vol. 14, no. 3, 2026, pp. i266-i271, https://doi.org/10.56975/ijcrt.v14i3.304033.
Chicago — 17th, bibliography
Balaga, Sowjanya, et al. "Explainable Machine Learning Framework for Predicting Employee Attrition and Layoffs in HR Management." International Journal of Creative Research Thoughts 14, no. 3 (2026): i266-i271. https://doi.org/10.56975/ijcrt.v14i3.304033.
Harvard — author–date
Balaga, S. et al. (2026) 'Explainable Machine Learning Framework for Predicting Employee Attrition and Layoffs in HR Management', International Journal of Creative Research Thoughts, 14(3), pp. i266-i271. Available at: https://doi.org/10.56975/ijcrt.v14i3.304033
IEEE — numbered reference
S. Balaga, R. Bhavani, V. Jandhyala and H. Srikanth, "Explainable Machine Learning Framework for Predicting Employee Attrition and Layoffs in HR Management," IJCRT, vol. 14, no. 3, pp. i266-i271, Mar. 2026, doi: 10.56975/ijcrt.v14i3.304033.
Vancouver — biomedical
Balaga S, Bhavani R, Jandhyala V, Srikanth H. Explainable Machine Learning Framework for Predicting Employee Attrition and Layoffs in HR Management. IJCRT. 2026 Mar;14(3):i266-i271. doi: 10.56975/ijcrt.v14i3.304033
AMA — 11th edition
Balaga S, Bhavani R, Jandhyala V, Srikanth H. Explainable Machine Learning Framework for Predicting Employee Attrition and Layoffs in HR Management. IJCRT. 2026;14(3):i266-i271. doi:10.56975/ijcrt.v14i3.304033
BibTeX — Zotero, Mendeley, LaTeX
@article{IJCRT2603999,
author = {Sowjanya Balaga and Reddymalla Bhavani and Vardhan Jandhyala and H Srikanth},
title = {Explainable Machine Learning Framework for Predicting Employee Attrition and Layoffs in HR Management},
journal = {International Journal of Creative Research Thoughts},
volume = {14},
number = {3},
pages = {i266-i271},
year = {2026},
month = {March},
issn = {2320-2882},
doi = {10.56975/ijcrt.v14i3.304033},
url = {https://doi.org/10.56975/ijcrt.v14i3.304033}
}
RIS — EndNote, RefWorks
TY - JOUR
AU - Balaga, Sowjanya
AU - Bhavani, Reddymalla
AU - Jandhyala, Vardhan
AU - Srikanth, H
TI - Explainable Machine Learning Framework for Predicting Employee Attrition and Layoffs in HR Management
T2 - International Journal of Creative Research Thoughts
JA - IJCRT
VL - 14
IS - 3
PY - 2026
SN - 2320-2882
DO - 10.56975/ijcrt.v14i3.304033
UR - https://doi.org/10.56975/ijcrt.v14i3.304033
SP - i266-i271
ER -
Issue
Volume 14 Issue 3,
March-2026
Pages : i266-i271
Article Information
- Pages
- i266-i271
- Published
- March 2026
- Registration ID
- IJCRT_304033
- Published Paper ID
- IJCRT2603999
- Research Area
- Science and Technology
- Author Type
- Indian Author
- Location
- Hyderabad, Telangana, India
- Peer Review
- Request Peer Review Report
- Licence
- CC BY 4.0 · Open Access
- ISSN & Impact Factor
- 2320-2882 · IF 9.17
- Downloads
- 176
- Permanent Link
- https://ijcrt.org/viewpaperforall.php?paper=IJCRT2603999
- Published Paper PDF
- https://ijcrt.org/papers/IJCRT2603999.pdf
Check for updates. Crossmark shows whether this article has been corrected, updated or retracted since publication, and links to the current version of record.
Summarise this Paper with AI
Opens your assistant with a prepared prompt. AI summaries can be incomplete or wrong — read the full paper before citing it.
Author Services
Certificates, printed copies and official reports for this paper
Published authors can request a hard copy of their certificate or of the printed journal, and obtain the transparent peer review and plagiarism reports for this article — each issued against this paper’s registration record.
Registration ID IJCRT_304033Printed copies
Hard Copy of CertificatePrinted certificate for each author, posted to you.
Hard Copy of JournalA bound printed copy of the issue this paper appears in.
Reports & recognition
Transparent Peer Review Report
The reviewer comments and decisions behind this article.
Turnitin Plagiarism Report
The similarity check run on this manuscript.
Best Paper Nomination
Put this article forward for the issue’s best paper award.
Requests are verified against the registration ID of this article.
About Publisher
International Journal of Creative Research Thoughts
Published by IJCRT Publication
2320-2882
ISSN
9.17
Impact Factor
2013
ESTD Year
Open
Access
Impact Factor 9.17, calculated from Google Scholar citation data — see how it is worked out.
An international scholarly open access journal: peer-reviewed, refereed, multidisciplinary, monthly and multilingual, with Crossref DOI registration, rich metadata and a citation generator. Verified indexing & discovery records.
IJCRT is a Transparent, Peer-Reviewed, Open Access Journal (Refereed Journal). Following the discontinuation of UGC and UGC-CARE journal listing, IJCRT is aligned with UGC’s Suggested Parameters for Choosing Peer-Reviewed Journals. UGC Public Notice
Licence
© 2026 — Authors hold the copyright of this article.
This work is licensed under a
Creative Commons Attribution 4.0 International License
and The Open Definition.
This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0),
which permits unrestricted use, distribution and reproduction in any medium, provided the original author and source are credited.
Disclaimer:
The content, data and findings in this article are based on the authors’ research and have been
peer-reviewed for academic purposes only. Readers are advised to verify all information before practical
or commercial use. The journal and its editorial board are not liable for any errors, losses or
consequences arising from its use.
Declarations
Funding
No external funding was received for this study.
Conflict of Interest
The authors declare that they have no conflict of interest.
Acknowledgements
The authors would like to thank the reviewers and the editorial board of International Journal of Creative Research Thoughts for their careful reading and constructive comments, and all colleagues who supported the preparation of this manuscript.
About the Journal
9.17Impact Factor
UGC AlignedSuggested Parameters
TransparentPeer Review
Open AccessNo Paywall
CrossrefDOI Available
Monthly12 Issues / Year
Since 2013Established
2320-2882ISSN
How Publication Works
1Submit Your PaperOnline or by email. A registration ID is issued straight away.
2Transparent Peer ReviewDouble-blind review by subject experts, reported openly.
3AcceptanceThe result reaches you by email and SMS against your registration ID.
4Published Open AccessFree to read worldwide, with certificate and letter ready to download.
Article Impact
63Views
44Downloads
107Total reads
Mar 2026Published
Published · 201 days ago
Today · last read today
2.5 views and 1.8 downloads per day over 25 days counted.
Counts exclude identified crawler traffic and repeat hits from the same reader within 30 minutes. Downloads reached directly through a search engine or an existing citation link are not included, so the figure is a conservative count of activity through this site. Full statistics
Discovery & Indexing
Find this paper on search engines and scholarly indexes, and check the journal’s verified records.
Find this paperSearch
Google ScholarExact-title search, with citing articles once indexed.Search
CrossrefThe registered DOI record and its metadata.Open DOI record
Semantic ScholarAI-powered literature search.Search- BASEBASEBielefeld Academic Search Engine — open-access harvester.Search
ResearchGateResearch network publication search.Search
Journal recordsVerified
“Search” opens a live search for this paper; “Verified” opens a journal record checked on the Indexing & Discovery page. Third-party services index at their own discretion, often several weeks after publication.
