Prediksi Churn Pelanggan pada Perusahaan Telekomunikasi Menggunakan Algoritma Pembelajaran Ensambel Berbasis Bagging
Submission Date: 2024-07-31 12:20:21
Accepted Date: 2024-11-26 06:49:55
Abstract
Perkembangan yang pesat dan munculnya banyak pesaing di industri telekomunikasi menuntut perusahaan untuk menerapkan strategi manajemen hubungan pelanggan yang efektif untuk mengatasi masalah churn yang dapat merugikan perusahaan. Churn adalah peristiwa berpindahnya pelanggan ke perusahaan lain karena alasan tertentu. Perusahaan harus mampu mengidentifikasi faktor-faktor yang memengaruhi pelanggan untuk melakukan churn karena biaya mempertahankan pelanggan lebih murah daripada memperoleh pelanggan baru. Salah satu upaya yang dapat dilakukan adalah membuat model prediksi churn bagi para pelanggannya. Dalam Tugas Akhir ini, model prediksi Boosted Bagging (BoBag) dipilih karena model ini menawarkan pendekatan ensambel berbasis bagging yang inovatif dengan hyperparameter yang dapat disesuaikan, seperti jumlah sampel, jumlah estimator, dan learning rate. Tugas Akhir ini menghasilkan sebuah model prediksi BoBag terbaik untuk kombinasi hyperparameter dengan jumlah estimator sebesar 200, jumlah sampel sebesar 0,5, dan learning rate sebesar 0,01. Kombinasi terbaik ini menghasilkan model dengan akurasi, F1, dan AUC berturut-turut sebesar 0,8589, 0,7112 dan 0,9176. Analisis terhadap model yang dihasilkan memberikan implikasi bahwa perusahaan harus memberikan perhatian khusus kepada para pelanggan bulanan dengan cara memberikan insentif atau diskon dan berusaha agar pelanggan tersebut bersedia untuk beralih ke kontrak yang lebih panjang. Selain itu, perusahaan harus tetap memperbaiki layanan internal agar dapat bersaing dengan para kompetitor di bidangnya.
Keywords
Bagging Ensambel; Boosted Bagging; Prediksi Churn; Telekomunikasi
CC Licencing
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 a Creative Commons Attribution License that allows others to share the work with an acknowledgement 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 acknowledgement 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 (See The Effect of Open Access).
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement 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 acknowledgement 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 (See The Effect of Open Access).
Refbacks
- There are currently no refbacks.
Jurnal Teknik ITS by Direktorat Riset dan Pengabdian Masyarakat (DRPM) ITS is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Based on a work at https://ejurnal.its.ac.id/index.php/teknik.
Statistik Pengunjung