Klasterisasi Rotational Churn terhadap Pelanggan Telekomunikasi Menggunakan Pendekatan Data-Centric AI

Abstract

In the current era of rapid technological development, customer churn poses a serious challenge, especially in the highly competitive telecommunications industry. Churn refers to customers who stop using a service or switch to another provider and can be categorized into three types: Active Churn, Passive Churn, and Rotational Churn. Rotational Churn, which is difficult to predict due to unclear reasons for stopping, is the primary focus of this study. This study aims to cluster Rotational Churn customers using a Data-Centric AI approach. This approach emphasizes improving data quality through Synthetic Data before applying the K-Means clustering algorithm. The data used in this study is churn data from a telecommunications company for the year 2023. The results show that clustering customers using the K-Means algorithm can provide deep insights into the characteristics of churn customers. The application of Data-Centric AI has been proven to improve the accuracy of the clustering model, ultimately helping the company to optimize programs and services to minimize churn and retain customers.