Evaluating Civil Servant Selection through Machine Learning Analysis of National Insight, General Intelligence, and Personal Characteristics Test Scores
DOI:
https://doi.org/10.26877/asset.v8i2.2300Keywords:
Classification, Logistic Regression, Machine Learning, Public Personnel Selection, Random Forest, XGBoostAbstract
This study analyzes the score distribution of 2,490 candidates in the 2024 Ministry of Finance Public sector recruitment, focusing on the CNI, GIT, and PCT sections using machine learning classification. Models used include Logistic Regression (accuracy 0.7897), Random Forest (0.9779), and XGBoost (0.9809), all trained with default parameters (n_estimators=100, max_depth=None) and evaluated using accuracy, precision, recall, and F1-score. While ensemble models outperformed Logistic Regression, the presence of false negatives—especially in the latter—reveals structural imbalances in test design. PCT scores dominate the total, while CNI and GIT show limited variation. These patterns suggest the need to revise PCT items with more complex ethical scenarios and enhance CNI and GIT content for better discrimination. This study contributes to improving test validity and fairness using empirical, data-driven methods. The findings support broader policy reforms toward more meritocratic and competency-aligned recruitment in Indonesia's civil service.
References
[1] Virnandes SR, Shen J, Vlahu-Gjorgievska E. Building public trust through digital government transformation: A qualitative study of Indonesian civil service agency. Procedia Comput Sci 2024;234:1183–91. https://doi.org/https://doi.org/10.1016/j.procs.2024.03.114.
[2] Pampouktsi P, Avdimiotis S, Μaragoudakis M, Avlonitis M. Applied Machine Learning Techniques on Selection and Positioning of Human Resources in the Public Sector. Open Journal of Business and Management 2021;09:536–56. https://doi.org/10.4236/ojbm.2021.92030.
[3] National Civil Service of Indonesia. Guidelines for the Implementation of the 2020 Civil Servant Candidate Selection. 2020.
[4] National Civil Service of Indonesia. Guidelines for the Implementation of the 2020 Civil Servant Candidate Selection. 2020.
[5] Kementerian Pendayagunaan Aparatur Negara dan Reformasi Birokrasi. Peraturan Menteri PANRB No. 27/2021 tentang Pengadaan Pegawai Negeri Sipil 2021.
[6] Pepple D, Makama C, Okeke J-P. Knowledge management practices: A public sector perspective. J Bus Res 2022;153:509–16. https://doi.org/https://doi.org/10.1016/j.jbusres.2022.08.041.
[7] Murphy KP. Machine Learning: A Probabilistic Perspective. Cambridge, MA, USA: MIT Press; 2012.
[8] Bui H. Assessment of Recruitment Records using Machine Learning. International Journal of Machine Learning and Networked Collaborative Engineering 2020;04:143–51. https://doi.org/10.30991/IJMLNCE.2020v04i04.001.
[9] Løkke Ann-Kristina, Villadsen Anders Ryom, Bach Anne Skipper. Recruitment and Selection in the Public Sector: Do Rules Shape Managers’ Practices? Public Pers Manage 2023;52:218–39. https://doi.org/10.1177/00910260221146145.
[10] Alsariera YA, Baashar Y, Alkawsi G, Mustafa A, Alkahtani AA, Ali N. Assessment and Evaluation of Different Machine Learning Algorithms for Predicting Student Performance. Comput Intell Neurosci 2022;2022:1–11. https://doi.org/10.1155/2022/4151487.
[11] Pessach D, Singer G, Avrahami D, Chalutz Ben-Gal H, Shmueli E, Ben-Gal I. Employees recruitment: A prescriptive analytics approach via machine learning and mathematical programming. Decis Support Syst 2020;134:113290. https://doi.org/10.1016/j.dss.2020.113290.
[12] Artar M, Balcioglu YS, Erdil O. Improving the quality of hires via the use of machine learning and an expansion of the person–environment fit theory. Management Decision 2024;ahead-of-print. https://doi.org/10.1108/MD-12-2023-2295.
[13] Nurhidayat R, Hendrastuty N. Analisis Sentimen Komentar Media Sosial Twitter Terhadap Tes CPNS dengan Algoritma Naive Bayes 2024;6:1477–89. https://doi.org/10.47065/bits.v6i3.6148.
[14] França TJF, Mamede HS, Barroso JMP, dos Santos VMPD. Artificial intelligence applied to potential assessment and talent identification in an organisational context. Heliyon 2023;9:e14694. https://doi.org/https://doi.org/10.1016/j.heliyon.2023.e14694.
[15] Zieky MJ. Designing Assessments for High-Stakes Selection: Balancing Reliability and Validity. Journal of Applied Testing Technology 2020;21:12–25. https://doi.org/10.1111/jatt.12345.
[16] Kementerian Pendayagunaan Aparatur Negara dan Reformasi Birokrasi. Peraturan Menteri PANRB No. 27/2021 tentang Pengadaan Pegawai Negeri Sipil 2021.
[17] Andy Hermawan, Aji Saputra. Analisis Pengaruh Variabel Nilai TIU, TWK, Dan TKP Terhadap Kelulusan SKD Pada Tes CPNS Menggunakan Analisa Bivariat Sederhana. Mars : Jurnal Teknik Mesin, Industri, Elektro Dan Ilmu Komputer 2024;2:46–58. https://doi.org/10.61132/mars.v2i1.64.
[18] Rahmawati UD, Sukmawati A, Kubota E, Wahyudi T. The Urgency of the National Insight Test as an Instrument for Assessment of Acceptance of the Corruption Eradication Commission. International Conference Restructuring and Transforming Law, vol. 2, Surakarta: UMS; 2023, p. 195–222. https://doi.org/10.1201/9781032622408-13.
[19] Raschka S, Mirjalili V. Python Machine Learning. 3rd ed. Birmingham, UK: Packt Publishing; 2019.
[20] Dai Z, Chang X. Predicting Stock Return with Economic Constraint: Can Interquartile Range Truncate the Outliers? Math Probl Eng 2021;2021:1–12. https://doi.org/10.1155/2021/9911986.
[21] Li W, Yang B. Three-way decisions with fuzzy probabilistic covering-based rough sets and their applications in credit evaluation. Appl Soft Comput 2023;136:110144. https://doi.org/10.1016/j.asoc.2023.110144.
[22] Veale M, Brass I. Administration by algorithm? Public management meets algorithmic governmentality. Journal of Public Administration Research and Theory 2019;29:121–36.
[23] Shahapure KR, Nicholas C. Cluster Quality Analysis Using Silhouette Score. 2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA), IEEE; 2020, p. 747–8. https://doi.org/10.1109/DSAA49011.2020.00096.
[24] Mangal K. The long-run costs of highly competitive exams for government jobs. J Dev Econ 2024;171:103331. https://doi.org/https://doi.org/10.1016/j.jdeveco.2024.103331.
[25] Pekdas IG, Uflaz E, Tornacı F, Arslan O, Turan O. Developing a machine learning-based evaluation system for the recruitment of maritime professionals. Ocean Engineering 2024;313:119406. https://doi.org/https://doi.org/10.1016/j.oceaneng.2024.119406.
[26] Li W, Yang B. Three-way decisions with fuzzy probabilistic covering-based rough sets and their applications in credit evaluation. Appl Soft Comput 2023;136:110144. https://doi.org/10.1016/j.asoc.2023.110144.
[27] Yang L, Huang J, Gao Q, Zhou Y, Hu M, Xie H. Dynamic Boundary Optimization of Free Route Airspace Sectors. Aerospace 2022;9:1–30. https://doi.org/10.3390/aerospace9120832.
[28] Seppälä Päivi, Małecka Magdalena. AI and discriminative decisions in recruitment: Challenging the core assumptions. Big Data Soc 2024;11:20539517241235870. https://doi.org/10.1177/20539517241235872.
[29] Arnesen S, Broderstad TS, Fishkin JS, Johannesson MP, Siu A. Knowledge and support for AI in the public sector: a deliberative poll experiment. AI Soc 2025;40:3573–89. https://doi.org/10.1007/s00146-024-02104-w.
[30] Zulfiqar FL, Prasetia T, Ulupui IGKA. Tax Incentives and Social Spending Amidst COVID-19: A VECM Analysis in a Subnational Government (case of Jakarta province, Indonesia). Journal of Tax Reform 2025;11:243–60. https://doi.org/10.15826/jtr.2025.11.1.200.
[31] Primawati P, Qalbina F, Mulyanti M, Yanuar F, Devianto D, Lapisa R, et al. Predictive Maintenance of Old Grinding Machines Using Machine Learning Techniques. Journal of Applied Engineering and Technological Science (JAETS) 2025;6:874–88. https://doi.org/10.37385/jaets.v6i2.6417.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Advance Sustainable Science Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
