Analysis of Churn Rate Significantly Factors in Telecommunication Industry Using Support Vector Machines Method

This research was intended to know factors that influenced the churn rate significantly in telecommunication company through research of historical billing and profiling data of customers. This study consisted of seven variables which are four billing historical variables and three profiling variables. The data was taken from a telecommunication company in Indonesia by taking active customer with minimum 6 months and historical data form January until March 2018. The data were tested using Support Vector Machine method by taking the result of classification performance either on performance of total variable or performance in each variable. The significance threshold was defined 5%. The results show that there were three variables that influenced the churn rate significantly namely voice usage, data usage and reload with performance percentage less than 5% of total performance. Those three variables were historical billing data.