Prediksi dan Pencegahan Risiko Burnout pada Pekerja Fleksibel Menggunakan Algoritma Random Forest
-
Noha Noor Fauziah Mk
*
Universitas Bina Sarana Informatika, Jakarta Pusat,
Indonesia
- Dimas Lukman Hakim Universitas Bina Sarana Informatika, Jakarta Pusat, Indonesia
- Ainun Cahyani Universitas Bina Sarana Informatika, Jakarta Pusat, Indonesia
- Findi Ayu Sariasih Universitas Bina Sarana Informatika, Jakarta Pusat, Indonesia
- Syifa Nur Rakhmah Universitas Bina Sarana Informatika, Jakarta Pusat, Indonesia
- Imam Sutoyo Universitas Bina Sarana Informatika, Jakarta Pusat, Indonesia (*) Corresponding Author
Abstract
Flexible workers operating under remote, hybrid, and freelance schemes face burnout risks that are difficult to detect early due to irregular work patterns and blurred work-time boundaries. Conventional burnout monitoring relying on manual surveys is static and lacks sensitivity to the dynamics of workers' psychological changes. This study aims to develop a machine learning-based burnout prediction system for flexible workers capable of providing real-time risk predictions accompanied by personalized prevention recommendations. The method employed is Random Forest Classifier using a dataset from Kaggle titled "Mental Health & Burnout in the Workplace" encompassing 5.000 observations. System development follows the Agile approach and is implemented through a Streamlit-based web application. Preprocessing stages include binary label transformation, data leakage elimination, one-hot encoding, class imbalance handling using SMOTE, and stratified split with a 90:10 ratio. The Random Forest model is configured with 800 trees, max_depth of 20, and other optimal hyperparameters. Evaluation results demonstrate that the model achieves 87% accuracy with precision of 0.89, recall of 0.91, and F1-score of 0.90 for the burnout class. Feature importance analysis identifies CareerGrowthScore, StressLevel, and ProductivityScore as dominant factors. The system provides real-time predictions with latency <2 seconds and prevention recommendations tailored to individual risk profiles. This research contributes a practical solution for self-monitoring mental health among flexible workers and provides organizations with an instrument for monitoring remote workforce well-being. Black-box testing validates that all functionalities operate according to specifications.
References
A. Patricia, Giriati, Syahbandi, R. Fauzan, and A. Jaya, “Pengaruh Work From Home Terhadap Job Satisfaction Karyawan Remote : Peran Work-Life Balance Dan Work Stress,” Bisnis dan Kewirausahaan, vol. 14, no. 1, pp. 75–89, 2025, doi: 10.37476/jbk.v14i1.4944.
A. Nuari and R. Modjo, “Beban Kerja dan Stres Kerja Karyawan Perusahaan di Masa Pasca COVID-19,” Penelit. Kesehat. Suara Forikes, vol. 14, no. 4, pp. 661–665, 2023, doi: 10.33846/sf14401.
A. Costin, A. F. Roman, and R. S. Balica, “Remote work burnout, professional job stress, and employee emotional exhaustion during the COVID-19 pandemic,” Front. Psychol., vol. 14, 2023, doi: 10.3389/fpsyg.2023.1193854.
G. Karakitsiou, S. Plakias, A. Tsiakiri, and K. Kedraka, “When Work Moves Home : Remote Work , Occupational Stress , Mental Health , Burnout and Employee Well-Being : Trends and Strategic Roadmap,” Psychol. Int., vol. 7, no. 4, pp. 1–24, 2025, doi: 10.3390/psycholint7040096.
A. Syakir, Q. Hasna, and Mawiza, “The Effect of Remote Working Fatigue on Turnover Intentions Among Millennial Employees in the Post- Pandemic Workplace,” Acta Psychol., vol. 4, no. 2, pp. 62–71, 2025, doi: 10.35335/psychologia.v4i2.83.
S. A. Trisnasari and D. A. Wicaksono, “Pengaruh Loneliness terhadap Job Stress Pekerja Work from Home (WFH) pada Masa Pandemi Covid-19,” Bul. Ris. Psikol. dan Kesehat. Ment., vol. 1, no. 2, pp. 1218–1226, 2021, doi: 10.20473/brpkm.v1i2.28444.
R. Siana, I. Pratiwi, S. Wartini, P. S. Manajemen, and F. Ekonomika, Flexible Working Arrangements : Fleksibilitas Kerja dalam Pengelolaan Sumber Daya Manusia ( SDM ) Modern. 2025. doi: 10.15294/msdm.v1i1.304.
R. Indradewa and A. Ayung, “The influence of flexible working arrangements and work-life balance on job satisfaction : A double-layered moderated mediation model The Government of Indonesia via its Spokesperson of the COVID-19 Management Task Unit , Wiku Adisasmito stated the revoca,” J. Ekon. dan Bisnis, vol. 26, no. 2, pp. 449–476, 2023, doi: 10.24914/jeb.v26i2.9551.
M. M. Amri, A. Maharani, and Z. Hidayah, “Job Burnout and Flexible Working Arrangement Associations on Employee Wellbeing With Perceived Organizational Support As Mediator: a Study During Pandemic,” J. Apl. Manaj., vol. 20, no. 3, pp. 594–610, 2022, doi: 10.21776/ub.jam.2022.020.03.11.
E. Demerouti, “Burnout : a comprehensive review,” Z. Arbeitswiss., vol. 78, no. 4, pp. 492–504, 2024, doi: 10.1007/s41449-024-00452-3.
M. P. Masduki, Ekawati, and I. Wahyuni, “Hubungan Antara Karakteristik Demografi Pekerja, Beban Kerja Mental, Dan Gaya Kepemimpinan Terhadap Burnout Pada Staff Administrasi FKM UNDIP,” J. Kesehat. Masy., vol. 9, no. 6, pp. 784–792, 2021, doi: 10.14710/jkm.v9i6.31435.
C. H. Saputra, A. Hermawan, and D. Avianto, “Prediksi Burnout Pada Programmer Menggunakan Teknik Prediction Of Burnout In Programmers Using Pattern Recognition,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 3, pp. 667–674, 2024, doi: 10.25126/jtiik2024118070.
M. M. Van Zyl-Cillié, J. H. Bührmann, A. J. Blignaut, D. Demirtas, and S. K. Coetzee, “A machine learning model to predict the risk factors causing feelings of burnout and emotional exhaustion amongst nursing staff in South Africa,” BMC Health Serv. Res., vol. 24, no. 1, 2024, doi: 10.1186/s12913-024-12184-5.
A. A. Hapsari, A. S. Nursuwanda, H. Zuhriyah, and D. J. Vresdian, “Klasifikasi Kesehatan Mental Mahasiswa Model TMAS dengan Algoritma Decision Tree , Logistic Regression , dan Random Forest,” Inform. dan Teknol., vol. 7, no. 2, pp. 55–64, 2024, doi: 10.37729/intek.v7i2.5690.
M. V. Popa et al., “An Integrated AI Framework for Occupational Health : Predicting Burnout , Long COVID , and Extended Sick Leave in Healthcare Workers,” Healthcare, vol. 13, no. 18, pp. 1–39, 2025, doi: 10.3390/healthcare13182266.
M. Grządzielewska, “Using Machine Learning in Burnout Prediction: A Survey,” Child Adolesc. Soc. Work J., vol. 38, no. 2, pp. 175–180, 2021, doi: 10.1007/s10560-020-00733-w.
M. Pillai et al., “Using an explainable machine learning approach to prioritize factors contributing to healthcare professionals’ burnout,” J. Intell. Inf. Syst., vol. 62, no. 4, pp. 1113–1124, 2024, doi: 10.1007/s10844-024-00862-z.
I. M. Widiarta, Y. Mulyanto, and A. Sutrianto, “Rancang Bangun Sistem Informasi Inventory Menggunakan Metode Agile Software Development ( Studi Kasus Toko Nada ),” Digit. Transform. Technol., vol. 3, no. 1, pp. 133–143, 2023, doi: 10.47709/digitech.v3i1.2549.
A. Zai, F. Lase, A. T. Harefa, and A. Harefa, “Penggunaan Teknik Umpan Balik ( Feedback ) dalam Membangun Kualitas Belajar Siswa,” J. Ilm. Ilmu Pendidik., vol. 7, no. 9, pp. 10824–10832, 2024, doi: 10.54371/jiip.v7i9.5858.
J. Shadiq, A. Safei, and R. W. R. Loly, “Pengujian Aplikasi Peminjaman Kendaraan Operasional Kantor Menggunakan BlackBox Testing,” Inf. Manag. Educ. Prof., vol. 5, no. 2, pp. 97–110, 2021, doi: 10.51211/imbi.v5i2.1561.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Prediksi dan Pencegahan Risiko Burnout pada Pekerja Fleksibel Menggunakan Algoritma Random Forest
Pages: 21 - 30
Copyright (c) 2025 Noha Noor Fauziah Mk, Dimas Lukman Hakim, Ainun Cahyani, Findi Ayu Sariasih, Syifa Nur Rakhmah, Imam Sutoyo
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).
