JOINT K-MEANS AND MODIFIED KNN FOR FAULT RESOLVING TIME PREDICTION OF TELECOMMUNICATION TROUBLE TICKET
Article Sidebar
Read Counter : 8
Download : 11
Main Article Content
Abstract
Efficiently resolving telecommunication trouble tickets is crucial for maintaining network reliability and customer satisfaction. This paper proposes a novel approach that combines the power of K-Means clustering and a modified K-Nearest Neighbors (KNN) algorithm to predict the fault resolving time of telecommunication trouble tickets. By leveraging K-Means clustering, the trouble tickets are grouped into clusters based on similarity, allowing for more accurate fault resolution time predictions within each cluster. The modified KNN algorithm further refines these predictions by considering the historical performance of similar tickets. Experimental results demonstrate that the joint K-Means and modified KNN approach significantly enhances the accuracy of fault resolving time predictions, thereby improving service quality and operational efficiency in telecommunication networks
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
[1] A. Z. Siregar, “Implementasi Metode Regresi Linier Berganda Dalam Prediksi Tingkat
Pendaftaran Mahasiswa Baru,” Kesatria J. Penerapan Sist. Inf. (Komputer dan Manajemen),
vol. 2, no. 3, pp. 133–137, 2021.
[2] R. E. Pranata, I. Gunawan, and Sumarno, “Algoritma Backpropagation Dalam Melakukan Prediksi Penjualan Beras Pada CV Hariara Pematangsiantar,” J. Comput. Syst. Informatics, vol. 2, no. 2, pp. 210–221, 2021.
[3] M. Ardhiansyah, “Penerapan Model Rapid Application Development pada Aplikasi Helpdesk Trouble ticket PT. Satkomindo Mediyasa,” J. Teknol. Sist. Inf. dan Apl., vol. 2, no. 2, p. 43, 2019, doi: 10.32493/jtsi.v2i2.2759.
[4] E. Muningsih, I. Maryani, and V. R. Handayani, “Penerapan Metode K-Means dan Optimasi Jumlah Cluster dengan Index Davies Bouldin untuk Clustering Propinsi Berdasarkan Potensi Desa,” J. Sains dan Manaj., vol. 9, no. 1, pp. 95–100, 2021.
[5] R. Muliono and Z. Sembiring, “Data Mining Clustering Menggunakan Algoritma K-Means Untuk Klasterisasi Tingkat Tridarma Pengajaran Dosen,” CESS (Journal Comput. Eng. Syst. Sci., vol. 4, no. 2, pp. 2502–714, 2019.
[6] H. D. Wijaya and S. Dwiasnati, “Implementasi Data Mining dengan Algoritma Naïve Bayes pada Penjualan Obat,” J. Inform., vol. 7, no. 1, pp. 1–7, 2020, doi: 10.31311/ji.v7i1.6203.
[7] P. A. Rahayuningsih, “Analisis Komparasi Algoritma Klasifikasi Data Mining,” J. Tek.
Inform. Kaputama, vol. 3, no. 1, 2019.
[8] S. Febriani and H. Sulistiani, “Analisis Data Hasil Diagnosa Untuk Klasifikasi Gangguan
Kepribadian Menggunakan Algoritma C4.5,” 89Jurnal Teknol. dan Sist. Inf., vol. 2, no. 4,
pp. 89–95, 2021.
[9] D. A. I. C. Dewi et al., “Penerapan Metode K-Means dan Optimasi Jumlah Cluster dengan Index Davies Bouldin untuk Clustering Propinsi Berdasarkan Potensi Desa,” J. Sains dan Manaj., vol. 9, no. 1, pp. 95–100, 2019, doi: 10.31940/matrix.v9i3.1662.
[10] Y. Pinanda, W. Firdaus Mahmudy, and E. Santoso, “Klasifikasi Risiko Penyakit pada Ibu Hamil menggunakan Metode Modified K-Nearest Neighbor (MKNN),” J. Pengemb. Teknlogi Inf. dan Ilmu Komput., vol. 6, no. 5, pp. 2116–2121, 2022.