A customer churn prediction model in telecom industry using Improved_XGBoost. (5th May 2023)

• Record Type: Journal Article
• Authors: Swetha, P.; Dayananda, R.B.
• Is Part Of: International journal of cloud computing. Volume 12:Number 2/4(2023)
• Page Start: 277
• Page End: 294
• Publication Date: 2023-05-05
• Subjects: telecommunication -- churn prediction -- customer churn -- XGBoost; Cloud computing -- Periodicals; 004.678205
• Languages: English
• ISSNs: 2043-9989

Abstract

Telecom industry has become part of human's daily routine, and the rapid increase over the last two decades results in tremendous competition among telecom service providers. Service providers should be aware of the features that make the customer to churn. In this research work, we developed a churn prediction model named Improved_XGBoost, with XGBoost as base model feature function is developed for efficient data handling. We evaluate our proposed model with two established and popular datasets, i.e., South Asia GSM and churn-big dataset. Furthermore, our proposed model achieved almost absolute accuracy of more than 99% considering the various performance metric such as accuracy, precision, recall, and F1-measure.