PreprintCC BY 4.0Zenodo
Employee Attrition Prediction and Risk Scoring System: An Explainable Machine-Learning Application
Abstract
This manuscript describes an explainable employee attrition prediction and risk-scoring application developed using Python, Logistic Regression, SHAP explanations, and Streamlit. The application provides a dashboard, employee-level risk profiles, department analysis, and what-if simulations. It is intended as an educational decision-support prototype, not as an automated employment decision system. Formal evaluation metrics and further validation are required before making claims about predictive performance or using the system operationally.
Related
- An explainable and fair TabNet framework for remote employee performance prediction using multidimensional workplace data
- Improving employee performance rating prediction using ANN probability-enhanced ensemble learning
- BREAKING THE BLACK BOX IN HEMATOPOIETIC STEM CELL TRANSPLANTATION: AN EXPLAINABLE MACHINE LEARNING WEB APPLICATION FOR PERSONALIZED SURVIVAL PREDICTION
- The application of explainable machine learning for the identification of MASLD in non-obese populations
- Machine learning-based prediction of compressive strength of wastewater-exposed concrete using explainable and optimized models
BibTeX
@misc{aditya2026employee,
title = {{Employee Attrition Prediction and Risk Scoring System: An Explainable Machine-Learning Application}},
author = {Aditya},
howpublished = {Zenodo},
year = {2026},
month = oct,
doi = {10.5281/zenodo.23441088},
url = {https://zenodo.org/records/23441088},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Employee Attrition Prediction and Risk Scoring System: An Explainable Machine-Learning Application
AU - Aditya
PY - 2026
DA - 2026/10/17
PB - Zenodo
DO - 10.5281/zenodo.23441088
UR - https://zenodo.org/records/23441088
AB - This manuscript describes an explainable employee attrition prediction and risk-scoring application developed using Python, Logistic Regression, SHAP explanations, and Streamlit. The application provides a dashboard, employee-level risk profiles, department analysis, and what-if simulations. It is intended as an educational decision-support prototype, not as an automated employment decision system. Formal evaluation metrics and further validation are required before making claims about predictive performance or using the system operationally.
ER -