Prediction of Dynamic Churn using Azure and Machine Learning

Customers are becoming more drawn to the quality of service (QoS) offered by businesses in the present. Yet, the greater rivalry is shown in present days in offering clients technologically cutting-edge QoS. Yet, effective customer relationship management systems can help the organization attract pr...

Full description

Saved in:
Bibliographic Details
Published in2023 2nd International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies (ViTECoN) pp. 1 - 6
Main Authors Bhasha, P., Reddy, R. Vishnuvardhan, Hamsaveni, P., Sravani, P. Hema, Nandan, N. Devakee, Samhitha, P.
Format Conference Proceeding
LanguageEnglish
Published IEEE 05.05.2023
Subjects
Cloud computing
Machine learning
Organizations
Quality of service
Radio frequency
Random Forest Algorithm and Support Vector Machines
Supervised learning
Support vector machines
Switches
Online AccessGet full text

Cover

More Information
Summary:Customers are becoming more drawn to the quality of service (QoS) offered by businesses in the present. Yet, the greater rivalry is shown in present days in offering clients technologically cutting-edge QoS. Yet, effective customer relationship management systems can help the organization attract preserve client connections, new clients, and increase customer loyalty by increasing revenue for business operations. The current proposed methodology mainly consisting of two components: Machine Learning and Cloud computing. The customer churn is predicted using the machine leaning techniques and further the SMS is sent to the customers who may have chances to unsubscribe from the network using Azure cloud. Furthermore, the client retention methods can benefit greatly from the use of machine learning models like SVM and RF algorithms.
DOI:10.1109/ViTECoN58111.2023.10157533