Employee Attribution Prediction Based on Machine Learning

DOI

10.2991/978-94-6463-823-3_30How to use a DOI?

Keywords

employee attrition prediction; machine learning; feature engineering; stacking ensemble

Abstract

Amid intensifying market competition and escalating employee attrition rates, many organizations are facing substantial financial and operational burdens. This study systematically evaluates machine learning approaches for turnover prediction using IBM’s benchmark HR dataset (1,470 observations, 35 initial features). Through feature engineering, three composite indicators—promotion potential, Stress Score, and Stability Index—were constructed to enhance the dataset. Correlation-based feature selection identified 15 key predictors from the enriched 38-variable feature space. The proposed stacking ensemble model, which strategically integrates Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Logistic Regression (LR), achieved superior classification performance, attaining 0.868 accuracy and 0.807 area under the Receiver Operating Characteristic curve (AUC-ROC), thereby outperforming individual baseline models. However, the significant class imbalance (only 16% positive attrition instances) constrained the model’s recall (0.261), underscoring persistent challenges in identifying minority-class cases. The framework offers interpretable human resources (HR) insights and practical utility but also highlights limitations in static data representation and the computational complexity of ensemble learning.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Shuwen Yang
PY  - 2025
DA  - 2025/08/31
TI  - Employee Attribution Prediction Based on Machine Learning
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 308
EP  - 317
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_30
DO  - 10.2991/978-94-6463-823-3_30
ID  - Yang2025
ER  -