IMPLEMENTASI ALGORITMA DECISION TREE UNTUK PREDIKSI CUSTOMER CHURN PADA LAYANAN TELEKOMUNIKASI MENGGUNAKAN ALTAIR AI STUDIO (RAPIDMINER)
DOI:
https://doi.org/10.66865/sahjvv53Abstract
Customer churn merupakan salah satu permasalahan utama dalam industri telekomunikasi yang dapat menyebabkan penurunan pendapatan perusahaan. Penelitian ini bertujuan untuk menerapkan algoritma Decision Tree dalam memprediksi customer churn menggunakan dataset Telco Customer Churn yang terdiri dari 7.043 data pelanggan. Proses pengolahan data dilakukan menggunakan Altair AI Studio (RapidMiner) melalui tahapan Retrieve Data, Set Role, Split Data, Decision Tree, Apply Model, dan Performance. Hasil penelitian menunjukkan bahwa model menghasilkan tingkat akurasi sebesar 75,77%. Berdasarkan hasil analisis Decision Tree, faktor yang paling berpengaruh terhadap churn adalah Contract, InternetService, TechSupport, dan Tenure. Pelanggan dengan kontrak bulanan, layanan Fiber Optic, dan tanpa TechSupport memiliki risiko churn tertinggi. Sebaliknya, pelanggan dengan kontrak dua tahun menunjukkan tingkat loyalitas yang tinggi. Hasil penelitian ini dapat digunakan sebagai dasar dalam penyusunan strategi retensi pelanggan pada perusahaan telekomunikasi.
Customer churn is one of the major challenges in the telecommunications industry. This study applies the Decision Tree algorithm to predict customer churn using the Telco Customer Churn dataset consisting of 7,043 customer records. The analysis process was conducted using Altair AI Studio (RapidMiner). The model achieved an accuracy of 75.77%. Contract type, Internet Service, Technical Support, and Tenure were identified as the most influential factors affecting customer churn. The results can support customer retention strategies in telecommunications companies.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Hawa Awalya Ghufron, Kevin Handerson, Yoseph Way, Dikdik Permana Wigandi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with Jurnal Komisi (Jurnal Komputer dan Sistem Informasi) 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 (CC BY-SA 4.0) 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.
Jurnal Komisi (Komputer dan Sistem Informasi) is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
