Simulasi Agent-Based dalam Prediksi Turnover dan Strategi Retensi Karyawan

Asfa Davissyah; Farel Indra Januart; Muhammad Ainul  Yaqin

doi:10.47134/jacis.v6i1.157

Authors

Asfa Davissyah Universitas Islam Negeri Maulana Malik Ibrahim Malang
Farel Indra Januart Universitas Islam Negeri Maulana Malik Ibrahim Malang
Muhammad Ainul Yaqin Universitas Islam Negeri Maulana Malik Ibrahim Malang

DOI:

https://doi.org/10.47134/jacis.v6i1.157

Keywords:

Manajemen Sumber Daya Manusia (SDM), Simulasi Berbasis Agen, Turnover Karyawan, Strategi Retensi, Pengembangan Karier

Abstract

Tingginya tingkat perputaran (turnover) karyawan menimbulkan tantangan operasional yang signifikan pada industri padat karya seperti peternakan ayam. Penelitian ini menerapkan metode Agent-Based Modeling (ABM) menggunakan sistem ERP berbasis spreadsheet untuk memprediksi dinamika turnover dan mengevaluasi efektivitas strategi retensi. Menggunakan data historis Human Capital, kami mensimulasikan perilaku 200 agen heterogen selama periode 24 bulan di bawah tiga skenario eksperimental: Baseline (Kontrol), Bonus Finansial, dan Jenjang Karir (Career pathing). Simulasi menunjukkan bahwa penerapan Career pathing menghasilkan penurunan tingkat turnover tahunan dari 70,65% (skenario kontrol) menjadi 60,87%, yaitu berkurang sebesar 9,78 poin persentase, sehingga menjadikannya intervensi paling efektif secara operasional. Temuan ini sejalan dengan literatur yang menyatakan bahwa pengembangan profesional mengurangi intensi keluar karyawan. Namun, analisis biaya-manfaat mengungkapkan sebuah paradoks: penerapan Career pathing secara universal menyebabkan defisit finansial yang masif akibat tingginya biaya retensi, sedangkan skenario Kontrol justru paling efisien secara finansial meskipun tingkat atrisinya tinggi. Studi ini menyimpulkan bahwa meskipun insentif non-finansial efektif menstabilkan tenaga kerja, penerapannya harus ditargetkan secara selektif menggunakan pendekatan berbasis data untuk menjamin kelayakan finansial

References

[1] S. Fukui et al., “Machine Learning with Human Resources Data: Predicting Turnover among Community Mental Health Center Employees,” J. Ment. Health Policy Econ., vol. 26, no. 2, pp. 63–76, 2023.

[2] C. Gao et al., “Large language models empowered agent-based modeling and simulation: a survey and perspectives,” Humanit. Soc. Sci. Commun., vol. 11, no. 1, 2024, doi: 10.1057/s41599-024-03611-3. DOI: https://doi.org/10.1057/s41599-024-03611-3

[3] P. Vuthi, I. Peters, and J. Sudeikat, “Agent ‑ based modeling ( ABM ) for urban neighborhood energy systems: literature review and proposal for an all integrative ABM approach,” Energy Informatics, vol. 5, no. 4, pp. 1–26, 2022, doi: 10.1186/s42162-022-00247-y. DOI: https://doi.org/10.1186/s42162-022-00247-y

[4] R. Cassidy et al., “Mathematical modelling for health systems research: A systematic review of system dynamics and agent-based models,” BMC Health Serv. Res., vol. 19, no. 1, pp. 15–17, 2019, doi: 10.1186/s12913-019-4627-7. DOI: https://doi.org/10.1186/s12913-019-4627-7

[5] R. N. Afdal, R. T. Simorangkir, and P. Harliana, “Pemodelan Arus Kendaraan Menggunakan Agent-Based Modeling: Studi Kasus Lalu Lintas Jalan Tuas Medan,” J. Pinter, vol. 9, no. 1, pp. 55–61, 2025, doi: 10.21009/pinter.9.1.8. DOI: https://doi.org/10.21009/pinter.9.1.8

[6] R. Shiri, A. El-Metwally, M. Sallinen, M. Pöyry, M. Härmä, and S. Toppinen-Tanner, “The Role of Continuing Professional Training or Development in Maintaining Current Employment: A Systematic Review,” Healthc., vol. 11, no. 21, pp. 1–17, 2023, doi: 10.3390/healthcare11212900. DOI: https://doi.org/10.3390/healthcare11212900

[7] Ștefan Ionescu, C. Delcea, N. Chiriță, and I. Nica, “Exploring the Use of Artificial Intelligence in Agent-Based Modeling Applications: A Bibliometric Study,” Algorithms, vol. 17, no. 1, 2024, doi: 10.3390/a17010021. DOI: https://doi.org/10.3390/a17010021

[8] S. T. Lindau et al., “Building and experimenting with an agent-based model to study the population-level impact of CommunityRx, a clinic-based community resource referral intervention,” PLoS Comput. Biol., vol. 17, no. 10, pp. 1–23, 2021, doi: 10.1371/journal.pcbi.1009471. DOI: https://doi.org/10.1371/journal.pcbi.1009471

[9] C. A. Arbelaez-Velasquez, D. Giraldo, and S. Quintero, “Analysis of a Teleworking Technology Adoption Case: An Agent-Based Model,” Sustain., vol. 14, no. 16, 2022, doi: 10.3390/su14169930. DOI: https://doi.org/10.3390/su14169930

[10] S. Mazzetto, “Interdisciplinary Perspectives on Agent-Based Modeling in the Architecture, Engineering, and Construction Industry: A Comprehensive Review,” MDPI - Build., vol. October, 2024, doi: 10.3390/buildings14113480. DOI: https://doi.org/10.3390/buildings14113480

[11] M. T. Robani, F. R. Aderiyana, N. S. Manahan, and M. P. Wilantara, “Analisis Literatur Mengenai Peran AI Agent dalam Efisiensi Automasi Digital,” JOISIE (Journal Inf. Syst. Informatics Eng., vol. 9, no. 1, pp. 77–89, 2025, doi: 10.35145/joisie.v9i1.4964. DOI: https://doi.org/10.35145/joisie.v9i1.4964

[12] P. Brady, “Comprehensive review,” Shipp. World Shipbuild., vol. 208, no. 4233, pp. 46–48, 2007, doi: 10.1201/9781003353034-6. DOI: https://doi.org/10.1201/9781003353034-6