CLUSTERING ROTATIONAL CHURN OF TELECOMMUNICATIONS CUSTOMERS USING A DATA-CENTRICAI APPROACH

Widang Muttaqin, Maya Silvi Lydia, Fahmi Fahmi

Abstract


Abstract: In the current era of very fast technological development, customer churn is a serious challenge, especially in the competitive telecommunications industry. Churn refers to customers who stop using a service or move to another provider, and can be categorized into three types: Active Churn, Passive Churn, and Rotational Churn. Rotational Churn, which is difficult to predict be- cause the reasons for stopping are unclear, is the main focus of this research. This research aims to group Rotational Churn customers using a Data-Centric AI approach. This approach emphasizes improving data quality through Confident Learning and Synthetic Data before being applied to the K-Means clustering algorithm. The data used in this research is customer churn data from one telecommunications company during 2023. The research results show that customer grouping using the K-Means algorithm can provide deep insight into the characteristics of customer churn. The application of Data-Centric AI is proven to be able to increase the accuracy of clustering models, which ultimately helps compa- nies optimize programs and services to minimize churn and retain customers.      

Keywords: data-centric AI; clustering; K-means

 

 

Abstrak: Dalam era perkembangan teknologi yang sangat pesat saat ini, churn pelanggan menjadi tantangan serius, terutama dalam industri telekomunikasi yang sangat kompetitif. Churn mengacu pada pelanggan yang berhenti menggunakan layanan atau beralih ke penyedia lain, dan dapat dikategorikan menjadi tiga jenis: Churn Aktif, Churn Pasif, dan Churn Rotasional. Churn Rotasional, yang sulit diprediksi karena alasan penghentian layanan tidak jelas, menjadi fokus utama penelitian ini. Penelitian ini bertujuan untuk mengelompokkan pelanggan Churn Rotasional menggunakan pendekatan Data-Centric AI. Pendekatan ini menekankan pada peningkatan kualitas data melalui Confident Learning dan Synthetic Data sebelum diterapkan ke algoritma K-Means clustering. Data yang digunakan dalam penelitian ini adalah data churn pelanggan dari satu perusahaan telekomunikasi selama tahun 2023. Hasil penelitian menunjukkan bahwa pengelompokan pelanggan menggunakan algoritma K-Means dapat memberikan wawasan mendalam tentang karakteristik churn pelanggan. Penerapan Data-Centric AI terbukti mampu meningkatkan akurasi model klastering, yang pada akhirnya membantu perusahaan mengoptimalkan program dan layanan untuk meminimalkan churn serta mempertahankan pelanggan.

 

Kata kunci: data-Centric AI; klasterisasi; K-means

 


Full Text:

PDF

References


“Customer: Definition and How to Study Their Behavior for Marketing.” Accessed: Nov. 13, 2023. [Online]. Available: https://www.investopedia.com/terms/c/customer.asp

B. A. Lukas and I. Maignan, “Striving for quality: The key role of internal and external customers,” J. Mark. Manag., vol. 1, no. 2, pp. 175–187, 1996, doi: 10.1007/bf00128689.

K. Coussement, S. Lessmann, and G. Verstraeten, A comparative analysis of data preparation algorithms for customer churn prediction: A case study in the telecommunication industry, vol. 95. Elsevier B.V., 2017. doi: 10.1016/j.dss.2016.11.007.

M. Óskarsdóttir, C. Bravo, W. Verbeke, C. Sarraute, B. Baesens, and J. Vanthienen, “Social network analytics for churn prediction in telco: Model building, evaluation and network architecture,” Expert Syst. Appl., vol. 85, pp. 204–220, 2017, doi: 10.1016/j.eswa.2017.05.028.

A. Amin et al., “Customer churn prediction in the telecommunication sector using a rough set approach,” Neurocomputing, vol. 237, pp. 242–254, 2017, doi: 10.1016/j.neucom.2016.12.009.

S. F. Bilal, A. A. Almazroi, S. Bashir, F. H. Khan, and A. A. Almazroi, “An ensemble based approach using a combination of clustering and classification algorithms to enhance customer churn prediction in telecom industry,” PeerJ Comput. Sci., vol. 8, 2022, doi: 10.7717/PEERJ-CS.854.

A. Ahmad and L. Dey, “A k-mean clustering algorithm for mixed numeric and categorical data,” Data Knowl. Eng., vol. 63, no. 2, pp. 503–527, 2007, doi: 10.1016/j.datak.2007.03.016.

F. Yang, “Data-centric AI : Perspectives and Challenges,” pp. 945–948.

“Data-Centric AI vs. Model-Centric AI • Introduction to Data-Centric AI.” Accessed: Nov. 19, 2023. [Online]. Available: https://dcai.csail.mit.edu/lectures/data-centric-model-centric/

C. G. Northcutt, L. Jiang, and I. L. Chuang, “Confident learning: Estimating uncertainty in dataset labels,” J. Artif. Intell. Res., vol. 70, pp. 1373–1411, 2021, doi: 10.1613/JAIR.1.12125.




DOI: https://doi.org/10.33330/jurteksi.v10i4.3304

Article Metrics

Abstract view : 71 times
PDF - 27 times

Refbacks

  • There are currently no refbacks.


Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK ROYAL 

Copyright © LPPM STMIK ROYAL

 

Lisensi Creative Commons
Ciptaan disebarluaskan di bawah Lisensi Creative Commons Atribusi-BerbagiSerupa 4.0 Internasional.