Comparative Study of Classification Algorithms for Customer Decisions on Telecommunication Products Using Supervised Learning

Abstract

Customers are the main goal of all business fields, without customers the company will not be able to continue or compete in the business field it is in, even though the company has brilliant products, if it does not have an increase in the number of customers the business will not be able to develop or even go bankrupt. Therefore, it is necessary to make observations and make applications that are able to predict customers who will subscribe so that companies can predict customers who will subscribe correctly without having to wait for confirmation from customers whose possibilities are still unknown. This can be very useful for any company because companies no longer need to look for random customers where it only takes time to find customers. PT. Telekomunikasi Indonesia with its product (Indihome) which is struggling to compete in the business world in the telecommunications and internet sector. Therefore research and development of this application are carried out so that PT. Indonesian telecommunications can get its customers quickly without having to spend a lot of money and effort. Making this application uses a classification method from machine learning technology based on customer historical data. The classification method has many strong algorithms for predicting variables that have more than 1 label. Some of the algorithms used are Logistic Regression, Random Forest Classifier, Support Vector Machine and Decision Tree which are provided by modules in the python programming language, namely SkLearn. The four algorithms will be tested with data balanced using the Oversampling method from the Smote algorithm to get optimal results in automatically predicting customers.