Open AccessChurn Analysis in Telecommunication Industry Customers Using Semiparametric and Non Parametric Survival Method
Author(s) -
Ade Vreyyuning Monika,
_ Indahwati,
Muhammad Nur Aidi
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1863/1/012034
Subject(s) - proportional hazards model , computer science , loyalty business model , survival analysis , hazard , accelerated failure time model , business , telecommunications , statistics , marketing , mathematics , service quality , chemistry , organic chemistry , service (business)
One of the challenges faced by Customer Relationship Management (CRM) of Telecommunication Company is customer retention efforts. The success rate of customer retention can be seen by the customer switching or churn process. Using the background and usage data related to the loyalty of the customers, it can be known the probability that customers will churn at a certain time. To overcome the problem, survival analysis will be carried out with parametric model using Cox Proportional Hazard and non-parametric using Support Vector Machine (SVM) for customer data. The data used in this study are customer data from telecommunication company who subscribe bundling package Internet and IPTV which are taken from 1000 customers in the Jabodetabek area. The time a customer is registered for the first time is defined as the start time and the last observation date is the end time. During the observation period, customer churn time is recorded. Based on the Kaplan Meier curve and log rank test, it is shows that there is a significant difference curve between customers with six different age categories. The results of the analysis found that SVM survival is able to compensate for Cox Proportional Hazard. Based on the result of the concordance index, the performance of the SVM survival has a better performance than Cox Proportional Hazard. One possibility that survival of SVM give a better performance is because the assumption of Cox Proportional Hazard is not met.