Implementation of the Random Forest and Naive Bayes Algorithms in Predicting Network Outages at the Kominfo South Tangerang

Raafa Syahidul Haq Irsi; Indra Kristianto

Authors

Raafa Syahidul Haq Irsi Universitas Pamulang
Indra Kristianto Universitas Pamulang

Keywords:

Machine Learning, Random Forest, Naive Bayes, Network Disruption Prediction, CRISP-DM

Abstract

The operational activities of the South Tangerang City Communication and Information Office (Diskominfo) rely heavily on a stable network infrastructure, making network disruptions a critical issue that directly affects service quality and employee productivity. The existing network monitoring system remains reactive and does not yet incorporate predictive analytics based on historical network capturing data. This study proposes a web-based network disruption prediction model using the Cross Industry Standard Process for Data Mining (CRISP-DM) framework by integrating a severity score and K-Means-based labeling to generate data-driven class labels before applying the Random Forest and Naïve Bayes classification algorithms. The dataset consists of 5,819 records collected from actual network traffic capturing within the operational environment of the South Tangerang City Communication and Information Office, using four primary network parameters: bandwidth, latency, packet loss, and uptime. After the data preparation stage, the Random Forest model achieved an accuracy of 95.78%, precision of 94.74%, recall of 97.63%, and an F1-score of 96.16%. In comparison, the Naïve Bayes model achieved an accuracy of 94.50%, precision of 92.88%, recall of 97.29%, and an F1-score of 95.03%. Feature Importance analysis identified packet loss as the most influential predictor, contributing 82.32% to the classification decision. Based on the overall evaluation, Random Forest demonstrated superior predictive performance and was deployed as the primary model in a Flask-based web application to support proactive network monitoring and network condition analysis.

Downloads

Download data is not yet available.

References

[1] K. Murphy, A. Lavignotte, and C. Lepers, “Fault Prediction for Heterogeneous Telecommunication Networks Using Machine Learning: A Survey,” IEEE Trans. Netw. Serv. Manag., vol. 21, no. 2, pp. 2515–2538, 2024, doi: 10.1109/TNSM.2023.3340351.

[2] M. M. Alamin, A. R. Firmansyah, A. Bittuqoh, C. B. Adzimi, M. I. Wahyudi, and M. Z. AT, “Pengukuran Performa Jaringan Internet Menggunakan Quality of Service dengan Wireshark,” Nusant. Comput. Des. Rev., vol. 3, no. 1, pp. 9–14, 2025, doi: 10.55732/ncdr.v3i1.1633.

[3] K. Putra, F., & Andesa, “Prediksi Nilai Redaman Jaringan Fiber Optik Untuk Menilai Kinerja Jaringan Menggunakan Random Forest Regression,” vol. x, no. x, pp. 3347–3361, 2025, [Online]. Available: https://doi.org/10.33022/ijcs.v14i2.4796

[4] A. K. Sah and K. Venkatesh, “Anomaly-Based Intrusion Detection in Network Traffic using Machine Learning: A Comparative Study of Decision Trees and Random Forests,” Proc. 2nd IEEE Int. Conf. Netw. Commun. 2024, ICNWC 2024, 2024, doi: 10.1109/ICNWC60771.2024.10537451.

[5] S. N. Ervansah, A. P. Kusuma, and Y. Primasari, “Penerapan Naive Bayes pada Sistem Pakar Pendeteksi Jaringan Internet di Rosi Cell.Net,” JASIEK (Jurnal Apl. Sains, Informasi, Elektron. dan Komputer), vol. 6, no. 2, pp. 167–176, 2024, doi: 10.26905/jasiek.v6i2.14049.

[6] Y. Yuliani, “Perbandingan Algoritma Klasifikasi untuk Deteksi Intrusi pada Jaringan Komputer (Literature Review),” J. Multidiscip. Inq. Sci. Technol. Educ. Res., vol. 1, no. 3c, pp. 1687–1695, 2024.

[7] R. Ben Said, Z. Sabir, and I. Askerzade, “CNN-BiLSTM: A Hybrid Deep Learning Approach for Network Intrusion Detection System in Software-Defined Networking With Hybrid Feature Selection,” IEEE Access, vol. 11, no. November, pp. 138732–138747, 2023, doi: 10.1109/ACCESS.2023.3340142.

[8] Elan Suherlan, Shindy Arti, Siti Nabilah, and Zahwah Hazimah, “Penerapan Flask Framework Untuk Deployment Model Machine Learning Dalam Mendukung Analisis Adaptasi Mahasiswa Pada Pembelajaran Daring,” PINTER J. Pendidik. Tek. Inform. dan Komput., vol. 9, no. 1, pp. 110–117, 2025, doi: 10.21009/pinter.9.1.15.

[9] A. Rianti et al., “CRISP-DM: Metodologi Proyek Data Science,” Pros. Semin. Nas. Teknol. Inf. dan Bisnis, pp. 107–114, 2023, [Online]. Available: https://ojs.udb.ac.id/index.php/Senatib/article/view/3015

[10] A. Pannadhitthana Candra, “Analisis Data Menggunakan Python: Memperkenalkan Pandas dan NumPy,” J. Inf. Syst. Educ. Dev., vol. 3, no. 1, pp. 11–16, 2025, doi: 10.62386/jised.v3i1.118.

[11] R. Syahri, T. Informatika, and S. Selatan, “Algoritma K-Means Clustering : Sebuah Studi Literatur K-Means Clustering Algorithm : a Literatur Study,” vol. x, no. x, pp. 1–7, 2023, doi: 10.12345/juri.

[12] A. Fauzan, N. Suarna, I. Ali, and H. Susana, “Penerapan Algoritma K-Means Clustering Untuk Meningkatkan Model Pengelompokan Dan Kinerja Jaringan Wi-Fi Secara Optimal,” J. Inform. dan Tek. Elektro Terap., vol. 13, no. 2, 2025, doi: 10.23960/jitet.v13i2.6272.

[13] R. More and J. S. Bradbury, “Assessing Data Augmentation-Induced Bias in Training and Testing of Machine Learning Models,” Proc. - 2025 IEEE Int. Conf. Softw. Anal. Evol. Reengineering - Companion, SANER-C 2025, pp. 57–60, 2025, doi: 10.1109/SANER-C66551.2025.00015.

[14] I. Saputri, P. Arsi, and K. N. Isnaini, “Effectiveness Hyperparameter Tuning on Random Forest, Linear Discriminant Analysis, Logistic Regression and Naive Bayes Algorithms for Detecting Dos Network Attacks,” J. Tek. Inform., vol. 6, no. 1, pp. 87–104, 2025, doi: 10.52436/1.jutif.2025.6.1.4175.

[15] W. Djatmiko, Kusrini, and Hanafi, “Perbandingan Naive Bayes dan Random Forest untuk Prediksi Perilaku Peserta Program Rujuk Balik,” J. Fasilkom, vol. 13, no. 3, pp. 358–367, 2023, doi: 10.37859/jf.v13i3.6070.

[16] D. Lusiyanti, S. Musdalifah, A. Sahari, and I. Al Fajri, “Evaluasi Kinerja Algoritma Machine learning pada Dataset Skala Besar,” MathVision J. Mat., vol. 7, no. 1, pp. 84–92, 2025, doi: 10.55719/mv.v7i1.1661.

[17] T. Adekoya-Cole, S. Fernando, A. Maroju, C. K. Samal, S. Aggarwal, and B. Brahma, “Building a dynamic opinion dashboard to categorize tweets for real-time sentiment analysis,” Int. J. Inf. Technol., vol. 18, no. 1, pp. 5–11, 2026, doi: 10.1007/s41870-025-02495-z.