Random Forest with Hyperparameter Tuning for a Teen Depression Risk Prediction System
DOI:
https://doi.org/10.24114/cess.v11i2.74393Keywords:
depression risk prediction; random forest; bayesian optimization; machine learning; SMOTE.Abstract
Early detection of vulnerability to depression during adolescence requires a precise computational approach. This study aims to design a web-based intelligent system architecture for predicting depression risk by analyzing lifestyle indicators and genetic parameters. The proposed methodology implements the Random Forest classification algorithm combined with the Synthetic Minority Over-sampling Technique (SMOTE) for data balancing. To maximize predictive performance, this study introduces an innovative intervention in the form of hyperparameter tuning using a Bayesian optimization approach. Computational testing results demonstrate that the Bayesian method successfully and significantly boosts the model’s accuracy, from 77.20% in the default configuration to 79.20%. The most crucial aspect of the originality and impact of this modeling is its ability to significantly reduce false-positive errors, as reflected by a Recall metric of 0.9643 specifically for the high-risk class. The full integration of this post-optimization algorithm into an interactive software interface confirms that this research does not merely present analytical outputs on paper but has successfully produced a functional, reliable, and ready-to-implement preventive screening tool for direct use in the community.
Downloads
References
[1] World Health Organization, “Mental health of adolescents,” World Health Organization. Accessed: May 25, 2026. [Online]. Available: https://www.who.int/news:room/fact-sheets/detail/adolescent-mental-health
[2] Gadjah Mada University & The University of Queenland, “Indonesia - National Adolescent Mental Health Survey (I-NAMHS) Report,” Yogyakarta, 2022. Accessed: May 25, 2026. [Online]. Available: https://acmhr.org/outputs/reports/12-i-namhs-report-bahasa-indonesia
[3] P. Y. Sari et al., “KONDISI KESEHATAN MENTAL REMAJA.” [Online]. Available: http://jurnal.globalhealthsciencegroup.com/index.php/JPPP
[4] Badan Kebijakan Pembangunan Kesehatan, “Fact Sheet Kesehatan Jiwa: Kesehatan Jiwa di Indinesia,” Jakarta, 2023. Accessed: May 25, 2026. [Online]. Available: https://repository.badankebijakan.kemkes.go.id/id/eprint/5532/
[5] J. Zhang, D. Liu, L. Ding, and G. Du, “Prevalence of depression in junior and senior adolescents,” Front. Psychiatry, vol. 14, 2023, doi: 10.3389/fpsyt.2023.1182024.
[6] A. Wahyudi Oktavia Gama, A. Degni Melsy Grren, I. Gusti Ngurah Darma Paramartha, G. Humaswara Prathama, N. Made Widnyani, and M. Wira Putra Dananjaya, “PENERAPAN ALGORITMA NAÏVE BAYES UNTUK PREDIKSI PENYAKIT DEPRESI PADA MAHASISWA.” [Online]. Available: http://jurnal.globalhealthsciencegroup.com/index.php/JLH
[7] Y. Cao et al., “Machine Learning Approaches for Mental Illness Detection on Social Media: A Systematic Review of Biases and Methodological Challenges,” 2025, International Society for Data Science and Analytics. doi: 10.35566/jbds/caoyc.
[8] E. Murakami, T. Shionoya, S. Komenoi, Y. Suzuki, and F. Sakane, “Cloning and characterization of novel testis-Specific diacylglycerol kinase η splice variants 3 and 4,” PLoS One, vol. 11, no. 9, Sep. 2016, doi: 10.1371/journal.pone.
[9] Fikri Muhamad Fahmi, Budiman Budiman, and Nur Alamsyah, “Optimizing IT Remote Workers Mental Health Prediction using Feature Engineering,” Int. J. Sci. Math. Educ., vol. 2, no. 2, pp. 01–09, Apr. 2025, doi: 10.62951/ijsme.v2i2.193.
[10] A. Alfahrizi Putra Arifiansyah, M. Afandi, D. Dwi Riskianto, and K. Kunci, “Prediksi Depresi Mahasiswa Menggunakan Algoritma Random Forest Berbasis Data Psikososial Depression Prediction Among University Students Using a Random Forest Algorithm Based on Psychosocial Data,” Jurnal Riset Sistem dan Teknologi Informasi (RESTIA), vol. 4, no. 1, pp. 12–21, 2026.
[11] D. Nickson, C. Meyer, L. Walasek, and C. Toro, “Prediction and diagnosis of depression using machine learning with electronic health records data: a systematic review,” BMC Med. Inform. Decis. Mak., vol. 23, no. 1, Dec. 2023, doi: 10.1186/s12911-023-02341-x.
[12] D. S. Sonnadara, S. D. Viswakula, and M. D. T. Attygalle, “A machine learning approach for predicting the depression status among undergraduates: A case study from Sri Lanka,” Nov. 16, 2023. doi: 10.21203/rs.3.rs-3555106/v1.
[13] M. Arifin and S. Adiyono, “Hyperparameter Tuning in Machine Learning to Predicting Student Academic Achievement,” 2024. [Online]. Available: http://ijair.id
[14] B. Ramadhan and S. F. Pane, “Pengaruh Hyperparameter Tuning untuk Efektivitas pada Pendekatan Hybrid dalam Mendiagnosis Stres dan Depresi : Tinjauan Studi Literatur,” Jurnal Tekno Insentif, vol. 18, no. 2, pp. 104–118, Dec. 2024, doi: 10.36787/jti.v18i2.1516.
[15] Z. Chen, D. Liu, W. J. Marrero, N. C. Jacobson, and T. Thesen, “A hierarchical Bayesian approach for predictive analytics of depression severity in medical students,” Healthcare Analytics, Jun. 2026, doi: 10.1016/j.health.2026.100453.
[16] S. Beekhani, “Teen social media usage and mental health,” Kaggle. Accessed: May 25, 2026. [Online]. Available: https://www.kaggle.com/datasets/sureshbeekhani/teen-social-media-usage-and-mental-
[17] G. M. Kim, S. Cha, M. Jung, and S. Kim, “Machine learning prediction of depression in culturally diverse families: Findings from the Korea Community Health Survey,” Front. Public Health, vol. 13, 2025, doi: 10.3389/fpubh.2025.1666084.
[18] H. U. Khan, A. Naz, F. K. Alarfaj, and N. Almusallam, “Analyzing student mental health with RoBERTa-Large: a sentiment analysis and data analytics approach,” Front. Big Data, vol. 8, 2025, doi: 10.3389/fdata.2025.1615788.
[19] D. Enkhbayar et al., “Explainable Artificial Intelligence Models for Predicting Depression Based on Polysomnographic Phenotypes,” Bioengineering, vol. 12, 2025, doi: 10.3390/bioengineering12020186.
[20] B. Zhang et al., “A refined SMOTE-ENN optimization method based on machine learning for heart rate variability data classification,” Front. Digit. Health, vol. 8, 2026, doi: 10.3389/fdgth.2026.1749570.
[21] C. Yu, X. Kong, W. Yu, X. Ni, J. Chen, and X. Liao, “Machine learning models for predicting the risk of depressive symptoms in Chinese college students,” 2025.
[22] K. O. Asare, Y. Terhorst, J. Vega, E. Peltonen, E. Lagerspetz, and D. Ferreira, “Predicting Depression From Smartphone Behavioral Markers Using Machine Learning Methods, Hyperparameter Optimization, and Feature Importance Analysis: Exploratory Study,” JMIR Form. Res., 2025.
[23] P. W. Simarmata and P. T. Prasetyaningrum, “Development of a Student Depression Prediction Model Based on Machine Learning with Algorithm Performance Evaluation,” Journal of Information Systems and Informatics, vol. 7, 2025, doi: 10.51519/journalisi.v7i2.1087.
[24] G. Zeng, “Invariance Properties and Evaluation Metrics Derived from the Confusion Matrix in Multiclass Classification,” Mathematics, vol. 13, 2025, doi: 10.3390/math13162609.
[25] A. P. Yan et al., “A roadmap to implementing machine learning in healthcare: from concept to practice,” Front. Digit. Health, vol. 7, 2025, doi: 10.3389/fdgth.2025.1462751.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 CESS (Journal of Computer Engineering, System and Science)
This work is licensed under a Creative Commons Attribution 4.0 International License.
