Telecom Churn Prediction
[1]Anuja Bachhav, [2]Sharayu Patil, [3]Manisha Yadav, [4]Liju Kunjumon, [5]Mr.S.T.Datir
[1] B. E Student, Department of Computer, Maratha Vidya Prasarak Samaj's Karmaveer Baburao Ganpatrao Thakare College of Engineering, Nashik, India
[2] B. E Student, Department of Computer, Maratha Vidya Prasarak Sam,aj's Karmaveer Baburao Ganpatrao Thakare College of Engineering, Nashik, India,
[3] B. E Student, Department of Computer, Maratha Vidya Prasarak Samaj's Karmaveer Baburao Ganpatrao Thakare College of Engineering, Nashik, India,
4] B. E Student, Department of Computer, Maratha Vidya Prasarak Samaj's Karmaveer Baburao Ganpatrao Thakare College of Engineering, Nashik, India,
5] B. E Professor, Department of Computer, Maratha Vidya Prasarak Samaj's Karmaveer Baburao Ganpatrao Thakare College of Engineering, Nashik, India
Abstract— Telecom churn has emerged because the single largest reason behind revenue erosion for telecommunication operators. Predicting churners from the demographic and behavioral data of customers has been a subject of active analysis interest and industrial practice. In the telecom sector due to a vast client base, a huge volume of data is being generated daily. Decision-makers and business analysts highlight that attaining new customers is more expensive than retaining the existing ones. Business analysts and customer relationship management (CRM) analyzers need to know the reasons for customer churn, as well as, behavior patterns from the existing data. This project proposes a churn prediction model that uses classification, as well as, clustering techniques to identify the churn customers and help to identify the factors behind the churning of customers in the telecom sector.
The most essential task of CRM is to create effective retention policies so as to prevent churners. After classification, the proposed model segments the churning customer’s data by categorizing the churn customers into different groups to provide group-based retention offers. This project also identifies churn factors that are essential in determining the root causes of churn. By knowing the churn factors from customer data CRM can improve productivity, recommend relevant promotions based on similar behavior patterns, and improve the marketing strategies of the company. The proposed churn prediction model is evaluated using metrics, such as accuracy, precision, recall, f-measure, and receiving operating characteristics (ROC) area.
KEYWORDS: Behavioral Analysis, Customer Churn Management, SVM, XGBoost
