NORMA eResearch @NCI Library

Developing promotional model using Customer Lifetime Value score to avoid Customer Churns

Shah, Shrey Sanjay (2020) Developing promotional model using Customer Lifetime Value score to avoid Customer Churns. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (507kB) | Preview
[img]
Preview
PDF (Configuration manual)
Download (908kB) | Preview

Abstract

Customer churn is one of the biggest problems that every telecom company is facing and measures are taken to avoid it. An approach to avoid customer churns has been implemented in this paper using the Customer Lifetime Value (CLV) data to give maximum waivers to eligible customers. CLV is basically defined as the total revenue that a customer has earned from start of his association with the company. Customer Lifetime Value (CLV) data has been calculated individually for each customer. These CLV scores are grouped in appropriate clusters with the help of k-means clustering algorithm. Then, all the probable churners are predicted with the help of decision tree resulting in an accuracy of 98%. All the customers that are predicted to be probable churners are given appropriate discounts or waivers based on the cluster assigned to them. Also, transfer learning has been implemented to check the consistency of the model over multiple datasets and it was observed that the performance of the model did not degrade significantly. These waivers and offers are provided to the customers well in advance before the customer churns, with an intention to retain maximum customers and avoid potential future churners.
Keywords – Telecom, Customer Churn, k-means clustering, decision tree, Customer Lifetime Value, Transfer Learning.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 21 Jan 2021 10:38
Last Modified: 21 Jan 2021 10:38
URI: http://norma.ncirl.ie/id/eprint/4417

Actions (login required)

View Item View Item