ISSN (Online) : 2456 - 0774

Email :

ISSN (Online) 2456 - 0774



Abstract:- Churn prediction systemusing classification as well as clustering techniques to classify churncustomers and the reasons behind the churning of telecom customers. In telecomindustry should we generate large amount of data on daily basis, it is verytedious task to mine such a kind of last data using specific data miningtechniques, while hard to interpret the prediction on classical techniques.Various researchers already described search a work to eliminate churn fromlarge data sets fusion static as well as dynamic approaches, but still suchsystems are facing many problems actual identification of churn. Sometime suchtelecommunication data may be containing some churn and, it is much necessaryto identify search problems. To successful identification of churn from largedata is providing effectiveness to customer relationship management (CRM). Inthis paper we proposed churn identification as well as prediction from largescale telecommunication data set using Natural Language Processing (NLP) andmachine learning techniques. First system deals with strategic NLP processwhich contains data preprocessing, data normalization, feature extraction andfeature selection respectively. Feature extraction techniques have beenproposed like TF-IDF, Stanford NLP and occurrence correlation techniques. Wheremachine learning classification algorithms are has used to train and test theentire module. Finally experiment analysis shows performance evaluation ofproposed system and evaluate with some existing systems.

Keywords: Natural language processing, churnprediction, machine learning, telecom industry, customer relationshipmanagement

Full Text PDF


Submit paper at

Paper Submission Open For April  20212
UGC indexed in (Old UGC) 2017
Last date for paper submission 30th April, 2022
Deadline Submit Paper any time
Publication of Paper Within 01-02 Days after completing all the formalities
Paper Submission Open For Publication /online Conference 
Publication Fees  
Free for PR Students