Prediksi Promosi Pegawai dengan Stacking Ensemble dengan SMOTE-ENN dan SHAP
-
Andri Yudha Pratama
*
Universitas Teknologi Yogyakarta, Sleman,
Indonesia
- Arief Hermawan Universitas Teknologi Yogyakarta, Sleman, Indonesia
- Donny Avianto Universitas Teknologi Yogyakarta, Sleman, Indonesia (*) Corresponding Author
Abstract
The paradigm of human resource management in the digital era demands an objective and data-driven employee promotion process. However, the extreme class imbalance (ratio 10.74:1) has the potential to introduce bias against minority groups that deserve promotion. This study proposes a stacking ensemble classification framework consisting of Random Forest, XGBoost, and LightGBM as base learners and Logistic Regression as a meta-learner, with the integration of SMOTE-ENN and two-level SHAP interpretability. This study shows that the application of SMOTE-ENN before cross-validation can result in a biassed performance estimate of up to +110% on the F1-Score; thus, the use of imblearn.Pipeline is proposed, which restricts resampling only to the training fold. Based on the evaluation using 10-fold stratified cross-validation free from data leakage, the stacking ensemble model achieved an accuracy of 0.9022, precision of 0.4342, recall of 0.4889, F1-score of 0.4598, and AUC-ROC of 0.8053. Although it did not achieve the highest F1 score, this model attained the best recall value among competitive models, making it relevant for contexts sensitive to false negative errors. SHAP analysis identifies avg_training_score, age, and performance_index as the main determinants of promotion decisions. The proposed framework provides a methodological contribution to model evaluation on imbalanced data while offering a more transparent and accountable decision support system to support the implementation of meritocracy in both government and corporate organisations.
Downloads
References
A. Benabou and F. Touhami, “Optimizing employee promotion predictions using machine learning,” International Journal of Production Management and Engineering, vol. 14, no. 1, pp. 16–33, 2026, doi: 10.4995/ijpme.2025.23364.
D. S. Angreni and M. Susanti, “Implementasi Data Mining Untuk Rekomendasi Kenaikan Pangkat Pegawai Negeri Sipil Menggunakan Algoritma Naïve Bayes Pada Biro Administrasi Pimpinan Sekretariat Daerah Provinsi Sulawesi Tengah,” Innovative: Journal Of Social Science Research, vol. 4, no. 1, pp. 9661–9674, Feb. 2024, doi: 10.31004/innovative.v4i1.9016.
A. Wang, “Enhancing HR management through HRIS and data analytics,” Applied and Computational Engineering, vol. 64, no. 1, pp. 222–228, 2024, doi: 10.54254/2755-2721/64/20241394.
S. Kurniawan, A. Nugroho, and Suherman, “Analisis Faktor yang Mempengaruhi Promosi Karyawan Menggunakan Random Forest pada Dataset Employee Promotion,” Jurnal Pustaka AI, vol. 5, no. 2, pp. 177–187, Aug. 2025, doi: 10.55382/jurnalpustakaai.v5i2.1115.
M. Isra, “Behavior Analysis and Prediction of Civil Services Staff in Occupational Functional Positions Using C4.5 Algorithm,” Jurnal Informasi dan Teknologi (jidt), vol. 4, no. 1, pp. 58–63, Feb. 2022, doi: 10.37034/jidt.v4i1.186.
F. Nuraeni, D. Kurniadi, and M. H. Diazki, “Algoritma K-Nearest Neighbor pada Kasus Dataset Imbalanced untuk Klasifikasi Kinerja Karyawan Perusahaan,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 11, no. 3, pp. 557–568, Jul. 2024, doi: 10.25126/jtiik.938144.
R. Ningsih, M. Devan Basunanda, and W. Erawati, “Implementasi Algoritma C4.5 Untuk Klasifikasi Tingkat Kenaikan Jabatan Pada PT Siprama Cakrawala Depok,” Jurnal Infortech, vol. 5, no. 1, 2025, doi: 10.31294/infortech.v7i1.25469.
F. Z. Abbour, E. M. Lghaouch, K. Mahjoubi, S. Ardchir, S. Ounacer, and M. Azzouazi, “Enhancing recruitment strategies with a hybrid AutoML approach to employee promotion prediction,” International Journal of Information Management Data Insights, vol. 6, no. 1, pp. 1–10, 2026, doi: 10.1016/j.jjimei.2026.100399.
A. I. Al-Alawi and M. S. Albuainain, “Machine Learning in Human Resource Analytics: Promotion Classification using Data Balancing Techniques,” in 2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS), IEEE, Jan. 2024, pp. 1–5. doi: 10.1109/ICETSIS61505.2024.10459566.
Y. Li, “Research on Faculty Manpower Management of vocational undergraduate based on Decision tree algorithm,” in Proceedings of the 2023 3rd International Conference on Education, Information Management and Service Science (EIMSS 2023), Atlantis Press, 2023, pp. 31–38. doi: 10.2991/978-94-6463-264-4_5.
M. B. Zhanuzakov, “Prediction of Employee Promotion Based on Ratings Using Machine-Learning Algorithms,” Bulletin of Abai KazNPU. Series of Physical and Mathematical sciences, vol. 77, no. 1, pp. 106–111, Mar. 2022, doi: 10.51889/2022-1.1728-7901.14.
E. D. Anggara, A. Widjaja, and B. R. Suteja, “Prediksi Kinerja Pegawai sebagai Rekomendasi Kenaikan Golongan dengan Metode Decision Tree dan Regresi Logistik,” Jurnal Teknik Informatika dan Sistem Informasi, vol. 8, no. 1, Apr. 2022, doi: 10.28932/jutisi.v8i1.4479.
S. Shafie, S. P. Ooi, and K. W. Khaw, “Prediction of Employee Promotion Using Hybrid Sampling Method with Machine Learning Architecture,” Malaysian Journal of Computing, vol. 8, no. 1, pp. 1264–1286, 2023, doi: 10.24191/mjoc.v8i1.18456.
Z. Xiong and W. Lu, “Employee Promotion Prediction: Machine Learning in HR Management,” Advances in Economics, Management and Political Sciences, vol. 241, no. 1, pp. 157–169, 2025, doi: 10.54254/2754-1169/2025.BJ30202.
N. E. Vijayan, “Automated Feature Engineering for Predictive HR Analytics Using Cloud-Based ETL and ML Pipelines,” Journal of Artificial Intelligence, Machine Learning and Data Science, vol. 1, no. 4, pp. 1–9, Nov. 2023, doi: 10.51219/JAIMLD/naveen-edapurath-vijayan/344.
M. Liu and X. Liu, “Design and Implementation of an Intelligent Employee Promotion Strategy Optimization System,” in Proceedings of the 2024 4th International Conference on Big Data, Artificial Intelligence and Risk Management, New York, NY, USA: ACM, Apr. 2024, pp. 515–520. doi: 10.1145/3718751.3718834.
J. and V.-R. Y. Tusell-Rey Claudia C. and Pino-Gómez, “Evaluative Customized Naïve Associative Classifier: Promoting Equity in AI for the Selection and Promotion of Human Resources,” in Intelligent Data Engineering and Automated Learning – IDEAL 2024, D. and Y. H. and A. J. M. and N. V. B. and N. P. and T.-B. A. Julian Vicente and Camacho, Ed., Cham: Springer Nature Switzerland, 2025, pp. 275–286. doi: 10.1007/978-3-031-77738-7_23.
P. Ardehkhani, S. R. Moslemi, and H. Hooshmand, “Enhancing Employee Promotion Prediction with a Novel Hybrid Model Integrating Convolutional Neural Networks and Random Forest,” in 2023 14th International Conference on Information and Knowledge Technology (IKT), IEEE, Dec. 2023, pp. 62–68. doi: 10.1109/IKT62039.2023.10433023.
P. Agrawal, S. Goyal, and A. Jandwani, “A novel agile based framework for employee promotion,” International Journal of Information Technology, vol. 16, no. 7, pp. 4481–4487, Jul. 2024, doi: 10.1007/s41870-024-02071-x.
Möbius, “HR Analytics: Employee Promotion Data.” Accessed: Mar. 31, 2026. [Online]. Available: https://www.kaggle.com/datasets/arashnic/hr-ana
D. Elreedy, A. F. Atiya, and F. Kamalov, “A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning,” Mach. Learn., vol. 113, no. 7, pp. 4903–4923, 2024, doi: 10.1007/s10994-022-06296-4.
P. Zhang, Y. Jia, and Y. Shang, “Research and application of XGBoost in imbalanced data,” SAGE Publications, vol. 18, no. 6, 2022, doi: 10.1177/15501329221106935.
M. Todorovic, N. Stanisic, M. Zivkovic, N. Bacanin, V. Simic, and E. B. Tirkolaee, “Improving audit opinion prediction accuracy using metaheuristics-tuned XGBoost algorithm with interpretable results through SHAP value analysis,” Appl. Soft Comput., vol. 149, p. 110955, 2023, doi: https://doi.org/10.1016/j.asoc.2023.110955.
R. Andespa, K. Sadik, C. Suhaeni, and A. M. Soleh, “Evaluating Random Forest and XGBoost for Bank Customer Churn Prediction on Imbalanced Data Using SMOTE and SMOTE-ENN,” Media Statistika, vol. 18, no. 1, pp. 25–36, 2025, doi: 10.14710/medstat.18.1.25-36.
S. Alam, M. S. Ayub, S. Arora, and M. A. Khan, “An investigation of the imputation techniques for missing values in ordinal data enhancing clustering and classification analysis validity,” Decision Analytics Journal, vol. 9, p. 100341, 2023, doi: 10.1016/j.dajour.2023.100341.
N. M. N. Mathivanan, E. F. Z. Xian, D. F. Yong Xi, and C. H. Kiat, “Impact of Feature Standardization on Heart Disease Prediction: A Comparative Analysis of Logistic Regression and Support Vector Machine Models,” Malaysian Journal of Computing, vol. 10, no. 2, pp. 2159–2175, 2025, doi: 10.24191/mjoc.v10i1.6835.
Y. D. Nugroho H, F. Zakiyabarsi, and A. J. Paramita, “Implementasi SMOTE-ENN dan Borderline SMOTE terhadap Performa LightGBM pada Imbalanced Class,” Rabit : Jurnal Teknologi dan Sistem Informasi Univrab, vol. 10, no. 1, pp. 51–59, 2025, doi: 10.36341/rabit.v10i1.5436.
G. Husain et al., “SMOTE vs. SMOTEENN: A Study on the Performance of Resampling Algorithms for Addressing Class Imbalance in Regression Models,” Algorithms, vol. 18, no. 1, pp. 1–16, 2025, doi: 10.3390/a18010037.
A. F. Salsabilah, B. Rahmat, and E. Y. Puspaningrum, “Stacking Ensemble of XGBoost, LightGBM, and CatBoost for Green Economy Index Prediction,” bit-Tech, vol. 8, no. 1, pp. 327–339, 2025, doi: 10.32877/bt.v8i1.2530.
J. Lei, J. Zhai, Y. Zhang, J. Qi, and C. Sun, “Supervised Machine Learning Models for Predicting Sepsis-Associated Liver Injury in Patients With Sepsis: Development and Validation Study Based on a Multicenter Cohort Study,” J Med Internet Res, vol. 27, p. e66733, 2025, doi: 10.2196/66733.
S. Q. Sultan, N. Javaid, N. Alrajeh, and M. Aslam, “Machine Learning-Based Stacking Ensemble Model for Prediction of Heart Disease with Explainable AI and K-Fold Cross-Validation: A Symmetric Approach,” Symmetry (Basel)., vol. 17, no. 2, 2025, doi: 10.3390/sym17020185.
D. Chicco and G. Jurman, “The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification,” BioData Min., vol. 16, no. 1, p. 4, 2023, doi: 10.1186/s13040-023-00322-4.
M. Imani, M. Joudaki, A. Bagheri, and H. R. Arabnia, “Why ROC-AUC Is Misleading for Highly Imbalanced Data: In-Depth Evaluation of MCC, F2-Score, H-Measure, and AUC-Based Metrics Across Diverse Classifiers,” Technologies (Basel)., vol. 14, no. 1, 2026, doi: 10.3390/technologies14010054.
S. Szeghalmy and A. Fazekas, “A Comparative Study of the Use of Stratified Cross-Validation and Distribution-Balanced Stratified Cross-Validation in Imbalanced Learning,” Sensors, vol. 23, no. 4, 2023, doi: 10.3390/s23042333.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Prediksi Promosi Pegawai dengan Stacking Ensemble dengan SMOTE-ENN dan SHAP
Pages: 1076-1087
Copyright (c) 2026 Andri Yudha Pratama, Arief Hermawan, Donny Avianto
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
