Classification of customer call details records using Support Vector Machine (SVMs) and Decision Tree (DTs)

Abstract

On a daily basis, telecom businesses create a massive amount of data. Decision-makers underlined that acquiring new customers is more difficult than maintaining current ones. Further, existing churn customers' data may be used to identify churn consumers as well as their behavior patterns. This study provides a churn prediction model for the telecom industry that employs SVMs and DTs to detect churn customers. The suggested model uses classification techniques to churn customers' data, with the Support Vector Machine (SVMs) method performing well 98.36 % properly categorized instances) and the Decision Tree (DTs) approach performing poorly 33.04 % and the decision tree algorithm deliver outstanding results