Customers Segmentation for Profitability Enhancement Using Data Mining Technique: The Case of ethio telecom
No Thumbnail Available
Date
2020-02-21
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
Customer segmentation is dividing of customers into groups of individuals that
have common characteristics or traits. By segmenting customers based on their
usage behavior, telecom companies can better target and classify their customers,
provide the services that meet their expectations and increase profitability. On the
contrary, companies with improper segmentation or luck of segmentation facing
the problem of providing the exact product or service to meet the actual customer
needs. Incorrect profit prediction and wastage of resource utilization are the main
problems of ethio telecom which results from poor customer segmentation.
To mitigate the segmentation problem this study focuses on segmenting telecom
customers based on their usage behavior using unsupervised clustering techniques.
K-means algorithm was used to cluster the Call Detail Record (CDR) data.
Before clustering CDR data were collected, relevant attributes selected and preprocessing
techniques such as data cleaning, data aggregation, data integration,
and data formatting were performed. In addition, four datasets were formed by
summarizing the data on a monthly base.
The experimentation results in eight different clusters. These clusters were analyzed
using quantile score techniques. The clusters were ranked and mapped with
customer segmentation type. Among the clusters, the cluster with 236
subscribers
was scored the highest in terms of duration, frequency and money. As a result,
this cluster was chosen as a platinum customer type. They are highly profitable
customers, vital to affect its revenue and need to serve well by the company.
Description
Keywords
CDR, cluster, Customer,K-means, Segmentation, unsupervised