ArticlePDF Available

Abstract and Figures

This article analyzes the impact of customer churn factors on improving the customer loyalty towards telecommunication service providers in Egypt. To accomplish this, a descriptive method is used. 1500 unique e-mails of customers of telecommunication service providers who have used telecommunication services of these providers were randomly selected. With a 25.6% response rate, the questionnaires were distributed through email and self-administered for data collection. Linear regression analysis was used on the responses. The results showed that there is a statistically significant relationship between customer churn factors and customer loyalty to improve factors and increase loyalty achievement to the telecommunication service providers in Egypt, The implications of the study are that the providers should better manage their relationships with the customers as a competitive policy in the telecommunication service marketplace. It can do that by customer churn management to decrease churn rate and increase customer loyalty.
Content may be subject to copyright.
DOI: 10.4018/IJCRMM.2019010104

Volume 10 • Issue 1 • January-March 2019
Copyright © 2019, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.
48




Hussein Moselhy Ahmed, Kafrelsheikh University, Kafr el-Sheikh, Egypt

This article analyzes the impact of customer churn factors on improving the customer loyalty
towards telecommunication service providers in Egypt. To accomplish this, a descriptive method
is used. 1500 unique e-mails of customers of telecommunication service providers who have used
telecommunication services of these providers were randomly selected. With a 25.6% response
rate, the questionnaires were distributed through email and self-administered for data collection.
Linear regression analysis was used on the responses. The results showed that there is a statistically
significant relationship between customer churn factors and customer loyalty to improve factors and
increase loyalty achievement to the telecommunication service providers in Egypt, The implications
of the study are that the providers should better manage their relationships with the customers as a
competitive policy in the telecommunication service marketplace. It can do that by customer churn
management to decrease churn rate and increase customer loyalty.

Churn Rate, Customer Churn Management, Customer Churn, Loyalty, Telecommunication Service

In today’s digital world and highly competitive between company, customer churn factors is an
important undertaking for each service provider to make long-term and profitable relationships with
specific customers (Coussement & Poel, 2008; Ngai, Xiu, & Chau, 2009). The service providers in
telecommunication industry suffer from attracting valuable customers with competitors; this is known
as customer churn. Lately, there have been many changes in the telecoms industry, Such as, customer
churn management for more profitable customers (Hung & Tsai, 2008).
In previous marketing studies (Coussement, Benoit & Van den Poel, 2010; Coussement & Van
den Poel, 2008; Berson, Simith, & Thearling, 2000), the average frequency is The proportion of
mobile operators are about 2% per month, which means 25% loss of their customer base within a year.
For the customer, cancellation costs are relatively small, given the fierce competition in the market,
which consists of providing similar services (in terms of price and quality) and offering discounts on
phones and other accessories. At present, the price is no longer different, as many service providers
tend to equalize each other’s prices. The main difference became additional services. Therefore, for
most mobile operators, the biggest challenge now is to switch from reactive to proactive; in other
words, to retain customers before deciding to terminate their contract and identify those high risk

Volume 10 • Issue 1 • January-March 2019
49
customers (Slavescu, 2011). Therefore, the current research examines the relationship between
customer churn factors and customer loyalty and how to improve the competitive position of the
service provider as well.

The objective is the desired level of attainment of any research or study or report (Mahtab, 2016),
So the current study has specific objectives:
To identify the impact of customer churn factors on customer loyalty.
To identify the impact of customer churn management on decrease churn rate and increase loyalty.
To identify the impact of integrated customer churn factors on loyalty.
Discover ways in which to manage customer churn.
Look for a solution that can increase consumer loyalty and prevent them to converting to
competitors.

In telecommunications service markets, customers may churn between the different providers in
Search for beast services and rates (Kiran Dahiya & Surbhi Bhatia, 2015). That is, the customer may
subscribe to a service provider for some period of time for thereafter subscribe to another provider
because the services offered by telecommunication service providers are very similar and easily
imitated by competitors, especially in these rapid technological developments.
In this case, service providers can distinguish themselves on price and quality only. But in fact,
competition on the basis of price and quality alone is not enough to retain the customer. Therefore,
customer churn management is the way to maintain existing customers and to achieve their very
important advantage in order to gain competitive advantage and continuity in this highly competitive
environment.Therefore, the main strategy for telecom service providers should be to focus on retaining
existing customers and attracting new customers.(Singh & Imran 2012) Singh and Imran (2012)
calculate that on average, online retailers lose 25% of their customers every year, and a small gain in
customer retention can increase earnings by more than 25%.Relationship marketing aims to create
lifetime customers because when customers experience a relationship with a troupe, they are ready
to forget any other competitors offer.
Customer loyalty is an important issue for the success of any telecommunication service provider,
because it is recognized that drawing new customers is more expensive than maintaining existing
ones, As explained above. Therefore, the main problem of the study revolves around the answer to
the following question:
“How to keep service provider clients in the current fierce competition and achieve their loyalty
through customer churn management”



The term “customer churn” is used in the Information and Communication Technology (ICT) industry
to refer to customers who are about to leave for a new competitor or terminate their subscription.
Predicting this behavior is very important for the real life market and competition as well, and it is very
important necessary to manage it, (Amjad Hudaib et al., 2015). The customer churn is closely related
to the customer retention rate and loyalty, (Buckinx & Van den Poel, 2005). Churn is the process of
converting customers to a less profitable product. With customer rates rising to 25% annually in some
global markets, identifying and retaining potential customers remains the paramount international

Volume 10 • Issue 1 • January-March 2019
50
priority for telecom managers. Markets are saturated, and customers who are unhappy with their use
of the service or reduce their power. By reviewing previous studies in this field, a number of factors
affecting the transformation of clients were found as is evident from Table 1:
From the previous table, the most important factors are: Cost of the conversion, quality,
competitors and technology, advertising, security dimension, price of service and satisfaction.
The Cost of the Conversion: It is delineated as the cost that incurs when prohibit customers desire
to switch to competitor’s services. (White & Yanamandram, 2007). In reality, when customers
switch to competitors, they mostly loose time, energy, and money even they may leave out from
some benefits and especial opportunities due to being the member of a specific organization.
Therefore, Switching service providers costs differences, and even excludes customers from
some benefits. Prices, if the customer experiences high conversion costs, and is forced to be
unusable (Hijazi Nia, 2013).
Quality: It refers to call quality consisting of text, video, and audio services provided by a
telecommunication provider (Ahn et al., 2006). Thus, It is one of the influential factors on
telecommunication provider’s customer churn.
Competitors & Technology: Competitors with high speed services are a big risk for every
company. Strong competition in the industry gives customers the opportunity to easily switch
from one supplier to another (Jones and Sasser, 1995). In other words, if satisfaction declines,
customers are keen to change their service provider (Jones, Mothersbaugh & Beatty, 2000).
Advertising: It is specified as a form of commendation of ideas, products, and services that
involves a fee (Kotler & Armstrong, 2000). Adequate advertising helps organizations attract loyal
customers and prevent our customers from churn (Hejazinia, 2013).
Security Dimension: It refers to the losing data or personal information (Hejazinia, 2013).
Security concerns usually result of distrust of the service provider. Also, trust means trusting
a trusted person (Cahill, 2007). As a result, customer mistrust leads to anxiety over security.
Price of Service: The price of the service refers to the amount of money the customer must pay
for the services. Actually, it is possible to say that the personal situation improves on the purchase
of customers (Anuwichanont, 2011) and the positive effects on customer churn.
Satisfaction: It is a mean customer value is perceived minus customer expectations (Oliver,
1980). In other words, if the customer feels that the value received is equal to his expectations,
satisfaction is created. Another way to determine the satisfaction of customers as a general attitude
towards customers towards the product or service after use (Jamal & Nasr, 2002). This customer
satisfaction helps to stay with the company and prevent customer churn.

In the past few years, there were revolutionary things have happened in the telecommunications field,
such as new services, technologies and open market liberalization to compete in the market. Because
the customer is the main source of profit, the way customers are managing fast wins is vital to the
survival and development of any telecommunications company, (Verbeke et al., 2011). At the same
time, an increase in the number of telecom service providers to large high-level organizations are
currently reducing the churn by focusing on customers independently as well. (Effendy & Baizal, 2014).
Churn can be both voluntary and involuntary, voluntary churn happens When an existing customer
leaves the company and joins a competing company, While at the involuntary churn customer is asked
by the company to leave due to reasons like customer can’t pay (Johny & Mathai, 2017).
The intent to transform customers into three types (Yang and Chiu, 2006) has been divided:
Involuntary churn: This occurs when customers fail to pay an invoice, and as a result, the service
provider quits the service.

Volume 10 • Issue 1 • January-March 2019
51
Table 1. Summary of researches relating to the customer churn factors
Customer Churn Factors Cost of the
Conversion
Quality Competitors
&Technology
Advertising Security
Dimension
Price of
service
Satisfaction
Keramati et.al (1988) × ×
Seo, Ranganathan and Babad (2008) × ×
Gerpott et al (2001) × ×
Ahn et al (2006) × ×
Kim and Yoon (2004) × × ×
Roya Hejazinia (2014) × × × × × × ×
Kim and Shin (2008) × ×
White and Yanamandram, (2007) ×
Jones and Sasser (1995) ×
Jones, Mothersbaugh and Beatty (2000) ×
Farsijani and zandi (2012) ×
Ahn, et.al, (2006) ×
Maleki & Darabi (2008) ×
Blech &Blech (2001) ×
Hejazinia (2013) ×
Source: Roya Hejazinia Mahdi Kazemi, 2014.

Volume 10 • Issue 1 • January-March 2019
52
Inevitable Churn: This happens when customers die or migrate, leading to the deletion of customers
from the market altogether.
Voluntary churn: This happens when customers prefer switching to another operator because of
more value.
Customer behavior is not independent, and their behavior depends on the behavior of those around
them (Zhang et al., 2012). With a saturated wireless market, acquiring new customers is difficult
and providers should focus more on retaining existing customers (Bersen et al., 2000). The telecom
industry is a huge, vibrant and dynamic industry with a very large base of customers, making customer
acquisition and retention an opportunity to survive and achieve better profitability.
Most of the studies in the field of communications have focused on the process of predicting
consumer behavior. Table 2 shows the most important of these studies.
From the above table, we see that most studies have been concerned with finding a model that
supports the decision maker in predicting customer churn in telecommunication service providers,
While there is a research gap in the study of the relationship between customer churn factors affecting
the loyalty of customers, which makes them not leave the service easily. Therefore, the current research
work to find a model to study the relationship between the influential factors and user loyalty.

From the literature review, we can find the number of factors that influence in customer churn, at the
same time, its influence in loyalty. So, we can suggest Conceptual framework: Impact of customer
churn factors on loyalty as Figure 1.

Q1: Is Customer Churn Factors (CCF) impact on the customer loyalty of telecommunication service
providers in Egypt?
H1) There is no significant positive effect on the dimensions of the factors affecting for Customer
churn on the customer loyalty of the telecommunication service providers in Egypt. It is divided
into the following sub-assumptions:-
(1/1) There is No significant impact of the Cost of Converting on the customer loyalty of the
telecommunication service providers in Egypt.
(1/2) There is No significant impact of the Quality of Service on the customer loyalty of the
telecommunication service providers in Egypt.
(1/3) There is No significant impact of Competitors and Advanced Technology on the customer
loyalty of the telecommunication service providers in Egypt
(1/4) There is No significant impact of Advertising on the customer loyalty of the telecommunication
service providers in Egypt.
(1/5) There is No significant impact of the Security on the customer loyalty of the telecommunication
service providers in Egypt.
(1/6) There is No significant effect of Price of Service on the customer loyalty of the telecommunication
service providers in Egypt.
(1/7) There is No significant effect of Satisfaction on the customer loyalty of the telecommunication
service providers in Egypt.
Q3: Is the dimensions of the factors affecting the customer churn combined impact on the customer
loyalty of the telecommunication service providers in Egypt?
H2) There is no significant positive effect of the dimensions of the factors affecting the customer
churn combined on the customer loyalty of the telecommunication service providers in Egypt.

Volume 10 • Issue 1 • January-March 2019
53
continued on following page
Table 2. Previous studies of customer churn
Researcher
Name
The title of the
study and its
variables
Objective of the study Sample Results
Diana Alomari
and Mohammad
Mehedi Hassan
2016
Predicting
Telecommunication
Customer Churn
Using Data Mining
Techniques
This study aimed at using data mining
techniques to predict the structure of
the transformation of wireless and
telecommunications customers. With
good analysis and interpretation of
data, value knowledge and key insights
in achieving and meeting customer
needs
Case study of 10,000
customers from Mobily
Telecom in Saudi
Arabia
This study found that RULES Family
Algorithm, which has never been used
in predicting the client’s transformation
structure, can predict the transformation
structure and give a reasonable
resolution result, although it gave a less
accurate result than the neural network
and resolution tree, but the difference
was less From 1%. Thus, the true
purpose of this paper was found that did
not prove that family algorithm rules
-6 better or worse than the widely used
techniques
Aim´ee Backiel,
Bart Baesens,
and Gerda
Claeskens
2015
Predicting Time-
To-Churn of
Prepaid Mobile
Telephone
Customers Using
Social Network
Analysis
This study aimed to integrate social
networking information into prediction
models and transformation structure
to improve accuracy, timeliness,
and profitability. Traditional models
are built using customer attributes,
but these data are often incomplete
for prepaid customers. Therefore,
the current chart record is called
to all customers so that charts can
be analyzed. A procedure has been
developed to build
Call the graph and extract the
relevant features from it to use in the
classification models.
Study the case of
Belgium’s telecom
data collection with 1.4
million customers and
more than 30 million
calls per month
His study concluded that the integration
of social network features into the
forecasting model of the customer’s
transformation structure can enhance
the results of the general forecast
and improve profitability and using
both social network results in data
classification and profitability. Using
relative risk models, it is possible to
determine the probability of a shift
for each individual customer and for
each future time segment based on one
model. This enables targeted marketing
campaigns to be used to intervene with
a smaller group of customers in a timely
manner, resulting in lower costs and
greater potential rewards
Vishal Mahajan
Dr. Richa Misra
Dr. Renuka
Mahajan
2015
Review of Data
Mining Techniques
for Churn
Prediction in
Telecom
The aim of this study is to provide
different techniques for extracting
data used in multiple models for
customers. And summarize the
current communication literature
by highlighting the size of the
sample used, the variables of the
intention of transforming used and
the results of data extraction using
different techniques. Finally, the list
of the most popular techniques for
predicting the transformation structure
of communication as a decision
tree, regression analysis provides
a road map for new researchers to
build on new management model
transformation structure.
Study of nearly 100
recent press articles
starting in 2000
This study found that the various data
extraction techniques used with the
intention of transformation so far the
most popular are the tree of resolution,
Aladdarro neural network and mass
analysis. However, there is no clear
general consensus on the method
of prediction to be used on the data
collected. Furthermore, given the cost
involved, most of the studies in the
survey use a small sample of customer
records, which may undermine the
reliability and validity of the results
of the analysis. This means that an
experimental study with a larger data set
and additional dimensions may increase
the reliability of the result.
Xue Zhao
2015
Research on
E-Commerce
Customer
Churning
Modeling and
Prediction
This study aimed to discuss the
problem of forecasting the structure
of customer transformation in
e-commerce. The use of a single
prediction model to accurately predict
the loss of e-commerce customers
is difficult. In order to improve the
accuracy of forecasting in volatile
e-commerce, many methods and
models are used.
Study of two types of
prediction methods:
statistical analysis and
artificial intelligence.
Statistical analysis
includes linear
regression, time
series, cluster analysis,
decision trees, Bayesian
networks, etc. Artificial
intelligence technology
has the ability to self-
learn and non-linear
processing capabilities.
This study found that the use of a
single prediction model is difficult to
accurately reflect changes in customer
characteristics and customer intent.
Using the forecasting paradigm, we
can identify the reasons for the lack
of e-commerce, since by combining
algorithms and neural network model
we can obtain better results for
prediction
Roya Hejazinia
Mahdi Kazemi
2014
Prioritizing factors
influencing
customer churn
The aim of this study is to present
a new model for the intention of
transforming the customers of telecom
companies based on literature review
In this study, empirical
data were obtained from
“all mobile subscribers
in Zahedan, Iran”.
The number of mobile
customers in Zahedan
is exactly 87,000 and
based on the Cochran
formula the sample
must be 380 but for
more confidence a total
of 500 questionnaires
were distributed,
with 415 complete
questionnaires sent.
This study found that the quality
of service is the most important
factor followed by the satisfaction of
customers and competitors with high
technology and the cost of change
and advertising. As a result, if mobile
operators do not provide qualified
services, the likelihood of customers
switching will be higher than in other
cases. Another effective factor was
advertising which shows that a few
customers leave their mobile company
because of lack of advertising and
knowledge.

Volume 10 • Issue 1 • January-March 2019
54

The purpose of our study is to discover, explore and comprehend the key factors affecting the
Customer churn in Telecommunication Service Providers in Egypt. So, the researcher has created some
hypothesis at first, collected some data and test it, the researcher has collected data from customers
through electronic mail and self-administered for data collection and linear regression analysis was
used. The researcher adopted the research approach in two main stages of social research: descriptive
research stage and interpretative research stage. The first stage aims to clarify the concepts of the
study and identify the findings To study previous studies and conduct the exploratory study and then
identify the problem and suggest hypotheses. In the next stage, the researcher relied on the causal
or explanatory approach to clarify the relationship between independent and dependent research
variables and the conclusion of causal relations between them (Imam, 2010).

In this research population is composed of telecommunication Service customers operating in the
Egyptian market. The telecommunication Service Providers in the Egyptian market limited by the
Ministry of Communications and Information Technology. These companies are Vodafone, Orange,
Etisalat and WE (Edata). The number of customers of the four companies, according to the latest
statistics on the 1st of January 2018 about 98.24 million individuals.
Due to the large number of customers, the lack of a precise framework of customer data for mobile
operators operating in Egypt, and time and cost considerations that are a constraint on individual
research, the sampling method is based on the collection of the required data and the field study on
the customer. A total of 1500 users were randomly selected and an email list was sent to them. A
total of 384 valid lists was retrieved. The confidence factor is 95% and the error limits are 5%. The
Table 3 displays the distribution of the sample.
Researcher
Name
The title of the
study and its
variables
Objective of the study Sample Results
Vahid Dust
Mohammad,
Amir Albadvi
And
Babak
Teymorpur
2014
Predicting
Customer Churn
Using CLV in
Insurance Industry
The aim of this study is to present
a proposed model to identify the
important factors that cause customers
to shift into the insurance industry and
predict their future behavior
Case study of 144,706
clients in insurance
companies in Iran 75%
of the records was
used to generate the
predictive model and
the rest was used to
test the accuracy of the
model
The study found that 5 attributes
(payment number, batch value, customer
value, number of contracts and discount
rate) are the most important features
in modeling the client’s intentional
management of the insurance industry
in Iran. In other words, features like
The Demographic, the application of
the insured car has no beneficial effect
to the intention of turning customers.
Among the features extracted are the
number of payments and payments
and the amount of the discount has
the opposite effect to the intention of
turning customers and features such
as convenience have a direct impact.
Among these qualities are good policies
for discount rate, installment and make
customers have more contracts can be
very useful for success in managing the
intention of transformation.
Michael
Haenlein
2013
Social interactions
in customer
churn decisions:
The impact of
relationship
directionality
The aim of this study is to focus on
two elements of analysis, focusing on
the importance of social interactions
in customer retention within a targeted
social network, using the mobile
customer base and relying on details of
call records to investigate the behavior
of the intention of transformation.
A case study of a
sample of 3431 records
containing call details
to investigate the
intentional behavior of
the customer
This study reached:
1- Theoretical effects
Retention rates at the individual level
and customer age are positive for the
social network.
2 - Administrative effects
Provide useful information in the
context of predicting the structure
of transformation and managing it
proactively
3. Methodological contribution
Proposing an approach to include the
effects of continuous innovation in the
relative risk models Cox Proportional
Hazards models
Table 2. Continued

Volume 10 • Issue 1 • January-March 2019
55
The sampling unit is the one for which the required data is collected and the data is available.
The sampling unit of the current study is all customer of mobile phone service providers.

The researcher used the survey as a data collection tool, which is a list of well-prepared questions
that directed to the clients of the communication service providers in Egypt asking them to answer.
This list has been divided into three sections:
Section One: It relates to factors influencing in customer churn.
Section II: Relates to consumer loyalty.
Section III: personal characteristics of the customer as type, age, terms of dealing with service provide.
Factors affecting customer Churn: The researcher adopted the standard on which the study
(judge, 2013) was adopted in measuring the impact of the factors influencing customer churn. The
standard consists of 28 phrases that reflect seven dimensions of the factors influencing customer
churn in service provider, namely Cost of Converting (3 phrases), Quality of Service (5 phrases),
Competitors and Technology (4 phrases) Advertising (4 Phrases), Security (4 Phrases), Price of
Service (5 Phrases), Satisfaction (3 Phrases).
Loyalty of customers: Represents the loyalty of customers, consisting of 10 phrases, and relied on
the researcher on the scale on which the study (Shalaby, 2010) in measuring the factors influencing
customer churn in service provider of Egypt, because it has a high degree of honesty and consistency.

In order to gauge the various perspectives on the subject matter in detail, So, The researcher relied
on two types of data to achieve the objectives of the study, namely secondary data and preliminary
data. The following is a presentation of these two types of data:
Secondary Data: The data used by the researcher in crystallizing the problem and questions of
the study and formulation of hypotheses, and the composition of the theoretical framework of the
study and measurement of variables and in determining the society of the study and the distribution of
Figure 1. Conceptual framework: Impact CCF on customer loyalty

Volume 10 • Issue 1 • January-March 2019
56
vocabulary, and this data were collected by relying on books and scientific messages and periodicals
that dealt with the concept of loyalty and Customer Churn.
Preliminary Data: The preliminary data were obtained from the sample of the study sample to
identify the nature of the relationship between the factors influencing customer churn and loyalty.
The data were collected by relying on a survey list distributed to the customers of the mobile service
providers in Cairo. The data collection tool was designed through the theoretical framework and
previous studies, and through the standards adopted and designed by other researchers.

Statistical methods are used for analyzing data and testing hypotheses through the use of statistical
programs on the computer, including statistical package programs for social sciences such as SPSS
and AMOS, The following methods have been used:
(A) The descriptive analysis methods: The researcher relied on methods of descriptive analysis,
especially arithmetical and standard deviation, in analyzing and describing respondents’ responses
and presenting the values of variables studied.
(B) Alpha Correlation coefficient: to test the degree of reliability of multi-item measurements
in the present study.
(D) Regression analysis method: to test the impact of customer churn and loyalty.

The following are the results of the reliability test for the standards used in the study, and the validity
of the standards.
3.5.1. The Level of Stability and Confidence is a Measure of the Influencing Factors:
The results of the reliability analysis showed that the value of the alpha coefficient of the coefficient
of the influencing factors of customer churn was reached 0.93, and the alpha coefficient reached
showed a high degree of stability or reliability according to the basic sciences (Sarifi, 2001). The
most important variables were “Price of Service”, while “Quality” was the least stable among the
sub-variables of the influencing factors of customer churn. The table shows the high rates of honesty
for all the dimensions of the influencing factors of customer churn. The scale should be validated
as shown in Table 4.

After examining the correlation coefficients of the 10 loyalty phrases included in the Loyalty Scale, it
was decided to exclude the phrase (8) which states that (I will not switch to another service provider
despite the density of its ads and its enticing), since it has a total correlation coefficient with the
other variables In the same scale of less than 0.3.In order to improve the degree of reliability for the
same measures and after the deletion of the statement, it was decided to apply the method of alpha
Table 3. Distribution of the sample size
Sample Vocabulary Response rate Sample rate Response Sample Sample
Vodafone 23.4 36.7% 129 550
Orange 25.8 30% 116 450
Etisalat Misr 22.9 23.3% 80 350
We Telecom 32.6 10% 49 150
Total 25.5% 100% 384 1500

Volume 10 • Issue 1 • January-March 2019
57
coefficient again, and the results of the second attempt showed a change in the values of the alpha
coefficient of loyalty scales to (0.780), and reflect the alpha coefficient reached a high degree of
stability Or reliability according to the basic sciences, as shown in Table 5.
3.6.1. Third: The Results of Descriptive Analysis of the Study Variables
The descriptive characteristics of the study variables reflect the main statistical parameters, which
describe the characteristics of variables and include basic characteristics such as arithmetic mean
and standard deviation.
3.6.2. The Descriptive Analysis of the Study Variable of the Influencing Factors
This section deals with the descriptive analysis of the variable “influencing factors of customer churn”
and its different variables under study. In this light, the researcher used the statistical descriptive
method using both the arithmetic mean (as a measure of the central tendency) and the standard
deviation (as a measure of dispersion) 7 Key dimensions and each dimension contains a set of terms,
as shown in Table 6:
From the previous Table 6 is illustrated: that the arithmetic mean of the dimensions of the factors
affecting the customer churn from the service provider which is cost of the conversion, quality,
competitors & technology, advertising, security dimension, price of service, satisfaction was 3,849,
4,009, 3,515, 3,562, 3,162, 3,917, 3,347, respectively.
The arithmetic average of the cost of the conversion is 849, indicating the ability of the service
provider from the point of view of the customer to provide the service at the time requested by the
customer and with an accuracy that satisfies his ambition also reflects the extent of the service
provider’s obligations to the customer.
The arithmetic mean was highest for the quality factor (4,009), which is the largest average
arithmetic of the dimensions of the factors influencing the customer churn, which indicates that
the quality has an important impact on the customer churn. (3,515) demonstrating the impact of
competition and technology on customer churn as well.
The post-advertising average was 3,562, indicating that service providers are affected by
advertising. The mean of the security dimension is 3,162, which is the lowest average of the
dimensions of the customer churn, indicating this promise comes in the final stage in the impact on
the customer churn.
The arithmetic mean of satisfaction was 3,347, indicating the importance of consumer satisfaction
with the service in non-customer churn.

This section deals with the descriptive analysis of the loyalty variable of the telecommunication service
customers. Whereas, the researcher used statistical descriptive method, using both the arithmetic
mean (as a measure of the central tendency) and the standard deviation (as a measure of dispersion)
as shown in the following table:
Table 7 shows the arithmetic average of the customer loyalty index of 2.81, which is a neutral
arithmetic mean, indicating that customers are looking to shift from one service provider to another
with a neutral view.

The researcher used multiple regression analysis methods to test the hypotheses and test the first
hypothesis of the study, “There is no significant positive effect on the dimensions of the factors
affecting for Customer churn on the customer’s loyalty of the telecommunication service providers
in Egypt.”The first hypothesis was divided into seven sub-hypotheses, each testing the impact of

Volume 10 • Issue 1 • January-March 2019
58
the following factors influencing the intention of shifting customers from mobile service providers
in Egypt.The second hypothesis of the study examined the effect of the factors affecting the shift
of customers from the service provider to another service provider and their relationship to loyalty.
“There is no significant positive effect of the dimensions of the factors affecting the customer churn
combined on the customer loyalty of the telecommunication service providers in Egypt.”The following
are the tests of the study hypotheses to determine their validity:

Ha1: the impact of the Cost of the Conversion on loyalty, Table 8 shows the results of the multiple
regression analysis of the relationship between cost of conversion on loyalty. In order to test the
validity of the first sub-hypotheses (1/1) which states:
“There is no significant impact of the cost of converting on the customer loyalty of the
telecommunication service providers in Egypt.’
Table 8 shows the following:
The validity of the model used to clarify the effect relationship between the cost of turning the
customer to another service provider as an independent variable and the loyalty of the customer
as a dependent variable. The calculated value of (11,304), which is significant at a significant
Table 4. Evaluate the degree of internal consistency of factors affecting in customer churn (Reliability analysis outputs)
Independent
variable
Dimensions /
Measurement
First run Second run Self-
honesty
Number of
Statement
Alpha
coefficient
Number of
Statement
Alpha
coefficient
Influential
factorsin
customer
Churn
Cost of the
Conversion
3 0.81 3 0.81 0.90
Quality 5 0.76 5 0.76 0.87
Competitors
&Technology
4 0.85 4 0.85 0.92
Advertising 4 0.79 4 0.79 0.88
Security
Dimension
4 0.84 4 0.84 0.91
Price of service 5 0.91 5 0.91 0.95
Satisfaction 3 0.88 3 0.88 0.93
Total 28 0.93 28 0.93 0.96
Source: Statistical analysis results
Table 5. Evaluate the degree of internal consistency of customer loyalty (Reliability analysis outputs)
Independent
variable
Dimensions /
Measurement
The first attempt The second attempt Self-
honesty
Number of
Statement
Alpha
coefficient
Number of
Statement
Alpha
coefficient
Customer
Loyalty
Customer 10 0,592 9 0,780 0.88
Total 10 0,592 9 0,780 0.88
Source: Statistical analysis results

Volume 10 • Issue 1 • January-March 2019
59
Table 6. Statistical averages and standard deviations of the Variables of the influencing factors in customer churn
Variable Factors Affecting Customer churn Arithmetic mean Standard
deviation
General
direction
Order
Cost of the conversion
I will not join another mobile company because my family and friends are in my
current company. 3.7812 1.21389 Agree 2
I join another The current mobile service provider for the benefits I enjoy. 4.3047 .68093 Totally Agree 1
If the conversion cost of other companies is low, I will convert to another. 3.4609 1.14036 Agree 3
TOTAL 3.8490 .59315 Agree
Quality
My current mobile service provider gives me real services that meet the services
you expect. .58557 4.5469 Totally Agree 1
The current mobile service provider high quality lines to make a voice, video,
and text call so I can’t churn it. .95637 4.0547 Agree 2
The current mobile service provider has the ability to implement the service
undertaken reliably and accurately so I can’t churn it. 1.09519 4.0234 Agree 3
My current mobile service provider ready to support customers and provides fast
service so I can’t churn it. 1.28259 3.6328 Agree 5
The quality of service provided is an important factor in not leaving the service
provider. 1.08214 3.7891 Agree 4
TOTAL .58557 4.0094 Agree
Competitors &Technology
I think my mobile service provider is the best communication technology and the
lowest prices, So I can’t churn it. 3.6875 1.14618 Agree 2
I think my mobile service provider offer high speeds for internet connection, I
can’t churn it. 3.8125 1.04600 Agree 1
The current mobile service provider offer 4.5G technology. 3.1875 1.41560 Agree 4
I have a curiosity to know what other companies are offering from newer
technology from this company. 3.3750 1.27725 Agree 3
TOTAL 3.5156 .99595 Agree
Advertising
The current mobile service provider offers attractive ads with innovative offers. 3.8125 1.23193 Agree 1
I have a curiosity to know what other companies are offering from newer
technology from this company 3.7734 1.10055 Agree 2
The way ads are displayed positively or negatively affects retention of existing
subscribers 3.3281 1.05614 Agree 4
The current mobile service provider has advertisements offered just to get new
customers. 3.3488 1.19109 Agree 3
TOTAL 3.5620 .89911 Agree
Security Dimension
My mobile service provider taking into account the safety factor of your calls. 3.1434 1.43021 Neutral 2
My current service provider offers me different levels of security. 3.0698 1.32727 Neutral 4
The safety factor is a factor that makes me switch from the current service
provider, 3.3488 1.40953 Neutral 1
I do not care about the degree of safety provided by the service provider. 3.0891 1.39336 Neutral 3
TOTAL 3.1628 1.27767 Neutral
Price of service
The service price suitable with the service provided to me. So I can’t churn it. 3.7132 1.49288 Agree 5
Competitors’ prices fall, the company will be left to join a competitor. 3.9264 1.05786 Agree 3
The price paid for the service is greater than the expected price for the service. 4.0155 1.24122 Agree 2
I think the price of services continues as it is, will it be reconsidered to continue
or withdraw from the company. 4.0620 1.16199 Agree 1
The quality of service provided is an important factor in not leaving the service
provider. 3.8682 1.34587 Agree 4
TOTAL 3.9171 1.06713 Agree
Satisfaction
My satisfied with the services of your mobile company is very important. 3.8798 1.04616 Agree 1
The value my is getting from my current service provider equal to the expected
value. 3.1434 1.46249 Neutral 2
Usually I ask my family members and friends to join to my current service
provider. 3.0194 1.46941 Neutral 3
TOTAL 3.3475 1.15480 Neutral
Source: Statistical analysis results

Volume 10 • Issue 1 • January-March 2019
60
Table 7. Statistical averages and standard deviations of the loyalty variable of the telecommunication service customers
Loyalty variable of the telecommunication service
customers
Arithmetic
mean
Standard
deviation
General
direction
Order
I will switch from the current service provider to the
attractiveness of other service providers 2.7674 1.38649 Neutral 4
I will not deal with the current service provider. 3.0465 .92405 Neutral 3
I will not continue my dealings with the current service
provider 3.1085 .77148 Neutral 2
I will be moving to another telecom service provider whose
branch is more widespread. 2.4729 1.37276 Neutral 9
I will deal with an alternative service provider if there are more
services 2.6977 1.35293 Neutral 6
I will become an alternative service provider just to have a
convenient place to wait for the service 2.7054 1.24070 Neutral 5
I will become an alternative service provider just to provide
more material possibilities 2.6705 1.28596 Neutral 8
I will become a service provider with a lot of friends(word of
mouth) 2.6589 1.04376 Neutral 7
I will become an alternative service provider if I want to get an
iron telephone line 3.2364 1.12727 Neutral 1
TOTAL 2.81 .55299 Neutral
Source: Statistical analysis results
Table 8. The type and strength of the relationship between cost of conversion on loyalty (Multiple regression analysis)
Cost of Conversion on loyalty Regression
coefficient
Coefficient of
correlation
Coefficient of
determination
I will not join another mobile company because my family
and friends are in my current company. -0,001 -0,186 0,035
I join another The current mobile service provider for the
benefits I enjoy. -0.123** -0.294 0,086
If the conversion cost of other companies is low, I will
convert to another. -0,118** -0,288 0,083
Coefficient of correlation in model R -0,336
Determination factor in model R2 0,113
Calculated F value 11,304
Degrees of freedom (3،266،269)
Level of significance 0.000 ***
*Significant at 0.05** Significant at 0.01*** Significant at 0.001
Source: Statistical analysis results

Volume 10 • Issue 1 • January-March 2019
61
level of 0.001, and the value of R2 is 0.113, 11.3% of the variation in customer turnaround
intentions is explained, and the rest is due to another variable not covered by the model as well
as the standard error.
There is a statistically significant negative relationship between the cost of transferring the
customer to another service provider and the loyalty of the customer. The strength of this
relationship is about 33.6% (according to the correlation coefficient R in the model).
The most dependable reliability variables are the effect of the conversion cost of the service
respectively (I join another The current mobile service provider for the benefits I enjoy.), then
If the conversion cost of other companies is low, I will convert to another..) Then (I will not join
another mobile company because my family and friends are in my current company.).
It was decided to reject the null hypothesis that “There is no significant impact of the cost of
converting on the customer loyalty of the telecommunication service providers in Egypt” and
the alternative assumption was accepted, after the multi regression model showed that there is a
significant relationship at the level of statistical indication 0.001 between the cost of convertingas
as independent variable, and customer loyalty as a dependent variable.
Ha2: the impact of Quality of Service on loyalty: Table 9 shows the results of multiple regression
analysis of the relationship between quality of service provided and customer loyalty. In order to test
the validity of the first sub-hypotheses (1/2), which states:
‘There is no significant impact on the quality on the customer loyalty of the telecommunication
service providers in Egypt. ‘
Table 9 shows the following:
Table 9. The type and strength of the relationship between quality on the customer loyalty (Multiple regression analysis)
Quality of setvice on loyalty Regression
coefficient
Coefficient of
correlation
Coefficient of
determination
My current mobile service provider gives me real services
that meet the services you expect. -0,091* -0,195 0,038
The current mobile service provider high quality lines to
make a voice, video, and text call so I can’t churn it. -0.222*** -0,261 0,068
The current mobile service provider has the ability to
implement the service undertaken reliably and accurately so
I can’t churn it.
-0,180*** -0,084 0,007
My current mobile service provider ready to support
customers and provides fast service so I can’t churn it. 0,007 0,153 0,023
The quality of service provided is an important factor in not
leaving the service provider. -0.050 -0,144 0,020
Coefficient of correlation in model R -0,329
Determination factor in model R2 0.108
Calculated F value 6,391
Degrees of freedom (5،264،269)
Level of significance 0,000 ***
*Significant at 0.05; ** Significant at 0.01; *** Significant at 0.001
Source: Statistical analysis results

Volume 10 • Issue 1 • January-March 2019
62
The validity of the model used to explain the effective relationship between the quality of service
provided as an independent variable and the loyalty as a dependent variable. The calculated value
of)f(is 6,391, which is significant at a significant level of 0.001 and the value of)R2(is 10.8%. Thus,
reliability is explained by 10.8% In the loyalty of the customer to the mobile service provider,
and the rest is due to other variables not covered by the model in addition to the standard error.
There is a statistically significant negative relation between the quality of service provided and
customer loyalty, and the strength of this relationship is about 32.9% (according to the correlation
coefficients R in the model).
The highest quality of service variables explained for customer loyalty are (The current mobile
service provider high quality lines to make a voice, video, and text call so I can’t churn it.), then
(My current mobile service provider gives me real services that meet the services you expect.,
Then (My current mobile service provider ready to support customers and provides fast service
so I can’t churn it.).
As a result, it was decided to reject the null hypothesis that “There is no significant impact of
the quality on the customer’s loyalty of the telecommunication service providers in Egypt. ” and
the alternative hypothesis was accepted, after a model was shown Multiple regression analysis
There is a significant relationship at a statistical significance level of 0.001 (according to test F)
between effectiveness as an independent variable and the intentions of customer transformation
as a dependent variable.
Ha3: the impact of Competitors &Technologyon loyalty: Table 10 shows the results of multiple
regression analysis of the relationship between Competitors &Technologyand customer loyalty. In
order to test the validity of the first sub-hypotheses (1/3), which states:
‘There is no significant impact of competitors and advanced technology on the customer loyalty
of the telecommunication service providers in Egypt.’
Table 10 shows the following:
The value of the model used to explain the affective relationship between the competitors and the
technology as an independent variable and the loyalty of the customers as a dependent variable.
The value of calculated (f) is 6,446, which is significant at a significant level of 0.001, and the
value of (R2) is 0.089. Thus, the communication explains 8.9% of the variation in customer
loyalty, The rest is due to other variables not covered by the model in addition to the standard error.
There is a statistically significant negative correlation between competitors and technology and
between customer loyalty, and the strength of this relationship is about 29.8% (according to the
correlation coefficient R in the model).
The competitors’ variables and the most explanatory technology for customer loyalty are (I have a
curiosity to know what other companies are offering from newer technology from this company),
then I think my mobile service provider offer high speeds for internet connection, I can’t churn it.).
As a result, it was decided to reject the null hypothesis that “There is no significant impact of
competitors and advanced technology on the customer’s loyalty of the telecommunication service
providers in Egypt.” and the alternative hypothesis was accepted, after a model was shown
Multiple regression analysis that there is a significant relationship at a statistical significance
level of 0.001 according to the F test between competitors and technology as an independent
variable, and customer loyalty as a dependent variable.
Ha4: the impact of Advertising on loyalty: Table 11 shows the results of multiple regression
analysis of the relationship between Advertising and customer loyalty. In order to test the validity of
the first sub-hypotheses (1/4), which states:
‘There is no significant impact of Advertising on the customer loyalty of the telecommunication
service providers in Egypt.’

Volume 10 • Issue 1 • January-March 2019
63
Table 11 shows the following:
The value of the model used to explain the effect of the ad as an independent variable and
the loyalty of customers as a dependent variable. The value of calculated f is 8,703, which is
significant at a significant level of 0.001 and the value of R2 is 0.116. Thus, the ease of search
explains 11.6% of the variation in customer loyalty, The rest is due to other variables not covered
by the model in addition to the standard error.
There is a statistically significant negative relationship between advertising and customer loyalty,
and the strength of this relationship is about 34.1% (according to the correlation coefficients R
in the model).
The most widely used ad variables for customer loyalty are (I have a curiosity to know what
other companies are offering from newer technology from this company), then (The way ads are
displayed positively or negatively affects retention of existing subscribers (
In the foregoing, it was decided to reject the null hypothesis of ” There is no significant impact of
Advertising on the customer loyalty of the telecommunication service providers in Egypt ” The
alternative hypothesis was accepted, after the regression analysis model was shown Multivariate
that there is a significant relationship at a statistically significant level of 0.001 (according to
test F) between the declaration as an independent variable, and loyalty as a dependent variable.
Ha5: the impact of Security on loyalty: Table 12 shows the results of multiple regression analysis
of the relationship between Security and customer loyalty. In order to test the validity of the first
sub-hypotheses (1/5), which states:
‘There is no significant impact of the Security on the customer loyalty of the telecommunication
service providers in Egypt.’
Table 12 shows the following:
The value of the model used to explain the effective relationship of Security as an independent
variable and between customer Loyalty as a dependent variable. The value of calculated f is 4,911
which is significant at a significant level of 0.001 and the value of R2 is 0,069. Therefore, it is
clear that the compatibility explains 6.9% of the variation in customer loyalty. Refers to other
variables not covered by the model in addition to the standard error.
There is a negative and statistically significant relationship between Security and customer
Loyalty, and the strength of this relationship is about 26.3% (according to the correlation
coefficients R in the model).
The most common security variables for customer loyalty are My mobile service provider taking
into account the safety factor of your calls.).
In the foregoing, it was decided to Accepted the null hypothesis of “There is no significant
impact of the Security on the customer’s loyalty of the telecommunication service providers in
Egypt.” Multiple regression analysis model There is a significant relationship at statistical level
of 0.001 (according to F test) between security as an independent variable, and customer loyalty
as a dependent variable.
Ha6: the impact of Price of Service on Loyalty: Table 13 shows the results of multiple regression
analysis of the relationship between Price of Service and customer Loyalty. In order to test the validity
of the first sub-hypotheses (1/6), which states:
‘There is no significant effect of the Price of Service on the customer loyalty of the
telecommunication service providers in Egypt.’
Table 13 shows the following:

Volume 10 • Issue 1 • January-March 2019
64
The value of the model used to explain the affective relationship between the Price of Service
as an independent variable and the customer Loyalty as a dependent variable was calculated at
357,427, which is significant at 0.001, with a value of R2,537. Thus, the service price explains
Table 10. The type and strength of the relationship between Competitors &Technology on the Customer’s Loyalty (Multiple
regression analysis)
Competitors &Technology on Loyalty Regression
coefficient
Coefficient of
correlation
Coefficient of
determination
I think my mobile service provider is the best communication
technology and the lowest prices, So I can’t churn it. -0,018 -0,199 0,039
I think my mobile service provider offer high speeds for
internet connection, I can’t churn it. -0.112* -0,243 0,059
The current mobile service provider offer 4.5G technology. -0,050 -0,208 0,043
I have a curiosity to know what other companies are offering
from newer technology from this company. -0,161** -0,267 0,071
Coefficient of correlation in model R -0,298
Determination factor in model R2 0.089
Calculated F value 6,446
Degrees of freedom (4،265،269)
Level of significance 0,000 ***
*Significant at 0.05 **; Significant at 0.01 ***; Significant at 0.001
Source: Statistical analysis results
Table 11. The type and strength of the relationship between Advertising on the customer loyalty (Multiple regression analysis)
Advertising on loyalty Regression
coefficient
Coefficient of
correlation
Coefficient of
determination
The current mobile service provider offers attractive ads with
innovative offers. -0,005 -0,233 0,054
I have a curiosity to know what other companies are offering
from newer technology from this company -0,159** -0,330 0,108
The way ads are displayed positively or negatively affects
retention of existing subscribers -0,079* -0,306 0,093
The current mobile service provider has advertisements
offered just to get new customers. -0,004 -0,261 0,068
Coefficient of correlation in model R -0,341
Determination factor in model R2 0,116
Calculated F value 8,703
Degrees of freedom (4،265،269)
Level of significance 0,000 ***
*Significant at 0.05 ** Significant at 0.01 *** Significant at 0.001
Source: Statistical analysis results

Volume 10 • Issue 1 • January-March 2019
65
87.1% of the variation in customer loyalty, And the rest is due to other variables not covered by
the model in addition to the standard error.
There is a statistically significant negative relationship between the Price of Service and the
Loyalty of the customers, and the strength of this relationship is about 93.3% (according to the
correlation coefficients R in the model).
The Price of Service variables that most explain the customer loyalty are (I think the price of
services continues as it is, will it be reconsidered to continue or withdraw from the company.
In the foregoing, it was decided to accepted the null hypothesis that “There is no significant
effect of the Price of Service on the customer’s Loyalty of the telecommunication service providers
in Egypt.” The multiple regression model showed that there is a significant relationship at a statistical
significance level of 0.001 (according to test F) between Price of Service as an independent variable
and customer Loyalty as a dependent variable.
Ha7: the impact of Satisfactionon Loyalty: Table 14 shows the results of multiple regression
analysis of the relationship between Satisfactionand customer Loyalty. In order to test the validity of
the first sub-hypotheses (1/7), which states:
‘There is no significant effect of Satisfaction on the customer loyalty of the telecommunication
service providers in Egypt.’
Table 14 shows the following:
The validity of the model used to explain the relationship of Satisfaction as an independent variable
and the Loyalty of customers as a dependent variable. The value of f calculated to 137,931,
which is significant at a significant level of 0.001, and the value of R2 is 0.609. Therefore, it is
clear that the response explains 60.9% Customer Loyalty, and the rest is due to other variables
not covered by the model in addition to the standard error.
Table 12. The type and strength of the relationship between Security on the customer loyalty (Multiple regression analysis)
Security on Loyalty Regression
coefficient
Coefficient of
correlation
Coefficient of
determination
My mobile service provider taking into account the safety
factor of your calls. 0,129* 0,236 0,055
My current service provider offers me different levels of
security. 0,053 0,192 0,036
The safety factor is a factor that makes me switch from the
current service provider, 0,101* 0,236 0,055
I do not care about the degree of safety provided by the
service provider. 0,011 0,171 0,029
Coefficient of correlation in model R -0,263
Determination factor in model R2 0,069
Calculated F value 4,911
Degrees of freedom (4،265،269)
Level of significance 0.001 ***
*Significant at 0.05 ** Significant at 0.01 *** Significant at 0.001
Source: Statistical analysis results

Volume 10 • Issue 1 • January-March 2019
66
There was a statistically significant negative correlation between Satisfaction and Loyalty, and
the relationship was about 78% (according to the correlation coefficients R in the model).
The most common response variables for Satisfaction are (My satisfied with the services of your
mobile company is very important.).
In the foregoing, it was decided to reject the null hypothesis that “There is no significant effect
of Satisfaction on the Customer loyalty of the telecommunication service providers in Egypt.” and the
alternative assumption was accepted The multiple regression model showed that there is a significant
relationship at a statistical significance level of 0.001 (according to F test) between satisfaction as an
independent variable and customer loyalty as a dependent variable.

Table 15 shows the results of the multiple regression analysis of the relationship between customer
churn factors and customer loyalty. In order to test the validity of the second hypothesis of the study,
which states:
“There is no significant positive effect of the dimensions of the factors affecting the customer
churn combined on the customer loyalty of the telecommunication service providers in Egypt.”
Table 15. The type and strength of the relationship between Customer Churn Factors on the
customer’s Loyalty (Multiple regression analysis)
Table 15 shows the following:
The value of the model used to explain the affective relationship of customer churn factors as
an independent variable and between customer loyalty as a dependent variable. The value of
Table 13. The type and strength of the relationship between Price of Service on the customer Loyalty (Multiple regression
analysis)
Price of Serviceon Loyalty Regression
coefficient
Coefficient of
correlation
Coefficient of
determination
The service price suitable with the service provided to me. So
I can’t churn it. 0,087*** 0,187 0,034
Competitors’ prices fall, the company will be left to join a
competitor. 0,126*** 0,633 0,400
The price paid for the service is greater than the expected
price for the service. 0,190*** 0,748 0,559
I think the price of services continues as it is, will it be
reconsidered to continue or withdraw from the company. 0,111*** 0,827 0,683
The quality of service provided is an important factor in not
leaving the service provider. 0,193*** 0,821 0,674
Coefficient of correlation in model R 0,933-
Determination factor in model R2 0-, 871
Calculated F value 357,427
Degrees of freedom (5،264،269)
Level of significance 0.001 ***-
*Significant at 0.05 ** Significant at 0.01 *** Significant at 0.001
Source: Statistical analysis results

Volume 10 • Issue 1 • January-March 2019
67
calculated f is 756,128, which is significant at a significant level of 0.001 and the value of R2
is 0.953. Thus, customer churn dimensions explain 95.3% Of the variation in customer loyalty,
and the rest is due to other variables not covered by the model in addition to the standard error.
There is a negative and statistically significant relationship between the dimensions of customer
churn and customer loyalty. The strength of this relationship is about 97.6% (according to the
correlation coefficient R in the model). Expted Security and Price of Service.
The dimensions of customer churn that are most frequently interpreted as customer loyalty are
(privacy), and (response).
In the foregoing, it was decided to reject the null hypothesis that ” There is no significant positive
effect of the dimensions of the factors affecting the customer churn combined on the customer’s loyalty
of the telecommunication service providers in Egypt.” The alternative hypothesis was accepted, after
the multiple regression model showed that there was a relationship At the level of statistical significance
0.001 (according to the F test) between the dimensions of customer churn as an independent variable,
and customer loyalty as a dependent variable.

The result showed a positive impact of Service Quality, Satisfaction, Competitors & Technology,
Cost of Converting, Advertising on the Customer churn management and loyalty. At the same
time The result showed a negative impact of Security and price of service on the Customer churn
management and loyalty. So, Security factor and price have no effect on the loyalty of the consumer in
telecommunications companies in Egypt, because the presence of these two factors in all companies.
But the other factors have an important impact, Because of the continuing competition in many
industries, such as the mobile phone industry, they are turning away from competitors. his truth is, if
companies want to stay in their competitive world, they have to invest in keeping customers. Therefore,
in order to better manage the client, we want the institutions to know the customer’s behavioral falsity
and the self-determinants of a customer. If mobile operators do not provide qualified services, the
Table 14. The type and strength of the relationship between Satisfactionon the customer’s Loyalty (Multiple regression
analysis)
Satisfactionon Loyalty Regression
coefficient
Coefficient of
correlation
Coefficient of
determination
My satisfied with the services of your mobile company is
very important. -0,372*** -0,661 0,436
The value my is getting from my current service provider
equal to the expected value. -0,098*** -0,090 0,008
Usually I ask my family members and friends to join to my
current service provider. -0,258*** -0,323 0,104
Coefficient of correlation in model R -0,780
Determination factor in model R2 0,609
Calculated F value 137,931
Degrees of freedom (3،266،269)
Level of significance 0,000 ***
*Significant at 0.05 ** Significant at 0.01 *** Significant at 0.001
Source: Statistical analysis results

Volume 10 • Issue 1 • January-March 2019
68
potential for customer displacement will be higher than in other cases. The last effective factor was
the announcement that few customers were leaving the mobile phone company because of lack of
advertising and knowledge.
Customer Churn Factors On Loyalty Regression
coefficient
Coefficient of
correlation
Coefficient of
determination
Cost of the Conversion -0,034 -0,316 0,099
Quality -0,002 -0,211 0,044
Competitors &Technology -0,033 -0,267 0,071
Advertising -0,001 -0,322 0,103
Security Dimension 0,022 0,240 0,057
Price of service 0,599 0,918 0,842
Satisfaction -0,403*** -0,702 0,492
Coefficient of correlation in model R -0,976
Determination factor in model R2 0,953
Calculated F value 756,128
Degrees of freedom (7،262،269)
Level of significance 0,000 ***
*Significant at 0.05 ** Significant at 0.01 *** Significant at 0.001
Source: Statistical analysis results

Volume 10 • Issue 1 • January-March 2019
69

Ahn, J., Hana, S., & Lee, Y. (2006). Customer churn analysis: Churn determinants and Mediating effects of
partial defection in the Korean mobile telecommunications service industry. Telecommunications Policy, 30(10-
11), 552–568. doi:10.1016/j.telpol.2006.09.006
Aim’ee Backiel. (2015). Bart Baesens, and Gerda Claeskens. Predicting Time-To-Churn of Prepaid Mobile
Telephone Customers Using Social Network Analysis.
Hudaib, A., Dannoun, R., Harfoushi, O., Obiedat, R., & Faris, H. (2015). Hybrid Data Mining Models for
Predicting Customer Churn. Int. J. Communications, Network and System Sciences, 8, 91-96. Retrieved from
http://www.scirp.org/journal/ijcns doi:10.4236/ijcns.2015.85012
Anuwichanont, J. (2011). The Impact of Price Perception on Customer Loyalty in the Airline Context. Journal
of Business & Economics Research, 9(9), 37–49. doi:10.19030/jber.v9i9.5646
Berson, A., Simith, S., & Thearling, K. (2000). Building data mining applications for CRM. New York:
McGraw-Hill.
Buckinx, W., & Van den Poel, D. (2005). Customer base analysis: Partial detection of behaviorally loyal
clients in a non-contractual FMCG retail setting. European Journal of Operational Research, 164(1), 252–268.
doi:10.1016/j.ejor.2003.12.010
Hung, C., & Tsai, C. F. (2008). Market segmentation based on hierarchical self-organizing map for markets of
multimedia on demand. Expert Systems with Applications, 34(1), 780–787. doi:10.1016/j.eswa.2006.10.012
Cahill, D. L. (2007). Customer Loyalty in Third Party Logistics Relationships: Findings from studies in Germany
and USA. Springer.
Mathai, M. P. P. (2017). Customer Churn Prediction: A Survey. International Journal of Advanced Research
in Computer Science, 8(5).
Coussement, K., & Van den Poel, D. (2008). Churn prediction in subscription services: An application of support
vector machines while comparing two parameter-selection techniques. Expert Systems with Applications, 34(1),
313–327.
Coussement, K., Benoit, D. F., & Van den Poel, D. (2010). Improved marketing decision making in a customer
churn prediction Context using generalized additive models. Expert Systems with Applications, 37(3), 2132–2143.
doi:10.1016/j.eswa.2009.07.029
AlOmari, D., & Hassan, M. M. (2016, September). Predicting Telecommunication Customer Churn Using Data
Mining Techniques. In International Conference on Internet and Distributed Computing Systems (pp. 167-178).
Cham: Springer.
Ngai, E. W. T., Xiu, L., & Chau, D. C. K. (2009). Application of data mining techniques in customer relationship
management: A literature review and classification. Expert Systems with Applications, 36(2), 2592–2602.
doi:10.1016/j.eswa.2008.02.021
Effendy, V., & Baizal, Z. A. (2014). Handling imbalanced data in customer churn prediction using combined
sampling and weighted random forest. In 2014 2nd International Conference on Information and Communication
Technology (ICoICT) (pp. 325-330). IEEE.
Hejazinia, R. (2013). Identify the variables affecting the Telecommunication company’s Customers [thesis].
University of Sistan and Bluchestan.
Jamal, A., & Naser, K. (2002). Customer satisfaction and retail banking: An assessment of son of the key
antecedents of customer satisfaction in retail banking. International Journal of Bank Marketing, 20(4), 146–160.
doi:10.1108/02652320210432936
Jones, M. A., Mothersbaugh, D. L., & Beatty, S. E. (2000). Switching barriers and repurchase intentions in
services. Journal of Retailing, 76(2), 259–274. doi:10.1016/S0022-4359(00)00024-5
Jones, T. O., & Sasser, W. E. (1995). Why satisfied customers defect? Harvard Business Review, 73(6), 88–99.

Volume 10 • Issue 1 • January-March 2019
70
Coussement, K., & Van den Poel, D. (2008). Integrating the voice of customers through call center emails into
a decision support system for churn prediction. Information & Management, 45(3), 164–174. doi:10.1016/j.
im.2008.01.005
Dahiya, K. (2015). Surbhi Bhatia. Customer Churn Analysis in Telecom Industry.
Kotler, P., & Armstrong, G. (2000). The principle of marketing (International ed.). Prentice and Hall.
Haenlein, M. (2013). Social interactions in customer churn decisions: The impact of relationship directionality.
International Marketing Journal, 4(10).
Ngai, E. W. T., Xiu, L., & Chau, D. C. K. (2009). Application of data mining techniques in customer relationship
management: A literature review and classification. Expert Systems with Applications, 36(2), 2592–2602.
doi:10.1016/j.eswa.2008.02.021
Oliver, R. L. (1980). A cognitive model of the antecedents and consequences of satisfaction decisions. JMR,
Journal of Marketing Research, 91, 462–464.
Hejazinia, R., & Kazemi, M. (2014). Prioritizing factors influencing customer churn. Interdisciplinary Journal
of Contemporary Research in Business, 5(12), 227–236.
Singh, R., & Khan, I. A. (2012). An approach to increase customer retention and loyalty in B2C world.
International Journal of Scientific and Research Publications, 2(6), 1–5.
Slăvescu, E. O. (2011). The implementation of uplift modeling to telecommunications marketing campaigns. The
case of the Romanian mobile telecommunications market. In Proceedings of The 7th International Conference
Management of Technological Changes, Alexandroupolis, Greece.
Mohammadi, V. D., Albadvi, A., & Teymorpur, B. (n.d.). Predicting Customer Churn Using CLV in Insurance
Industry.
Mahajan, V., Misra, R., & Mahajan, R. (2015). Review of data mining techniques for churn prediction in telecom.
Journal of Information and Organizational Sciences, 39(2), 183–197.
Verbeke, W., Martens, D., Mues, C., & Baesens, B. (2011). Building comprehensible customer churn prediction
models with advanced rule induction techniques. Expert Systems with Applications, 38(3), 2354–2364.
doi:10.1016/j.eswa.2010.08.023
White, L., & Yanamandram, V. (2007). A model of customer retention of dissatisfied business services customers.
Managing Service Quality, 17(3), 298–316. doi:10.1108/09604520710744317
Zhao, X. (2014). Research on E-Commerce Customer Churning Modeling and Prediction. Open Cybernetics
& Systemics Journal, 8, 800–804.
Dr. Hussein Moselhy is an Associate Professor in the Department of Management at The University of Kafrelsheikh,
Egypt. He has experience in online marketing, search engine optimization, social media marketing, content
marketing, email marketing, web analytics, affiliate marketing, mobile marketing, website optimization, online
advertising, video marketing, big data analytics and market research techniques. He received a Bachelor’s in
Management in 1987 and a Master’s of management in Sciences in 1994 and a Doctor of Philosophy Management
Sciences and Information Technology in July 2002. He became an Associate Professor in 2010 in digital marketing.
His career involves managing the demands of large-scale projects in institutional development, core competency
assessment, capacity building and development, contract negotiations, human resources development, program
management and developing customized solutions that align with business needs. He has a strong understanding
of business processes and is able to rapidly discern and incorporate operational requirements into cutting-edge
solutions.
ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
Customer churn prediction is a core research topic in recent years. Churners are persons who quit a company's service for some reasons. Companies should be able to predict the behavior of customer correctly in order to reduce customer churn rate. Customer churn has emerged as one of the major issues in every Industry. Researches indicates that it is more expensive to gain a new customer than to retain an existing one. In order to retain existing customers, service providers need to know the reasons of churn, which can be realized through the knowledge extracted from the data. To prevent the customer churn, many different prediction techniques are used .The commonly used techniques are neural networks, statistical based techniques, decision trees, covering algorithms, regression analysis, kmeans etc. This paper surveys the commonly used techniques to identify customer churn patterns.
Article
Full-text available
Telecommunication sector generates a huge amount of data due to increasing number of subscribers, rapidly renewable technologies; data based applications and other value added service. This data can be usefully mined for churn analysis and prediction. Significant research had been undertaken by researchers worldwide to understand the data mining practices that can be used for predicting customer churn. This paper provides a review of around 100 recent journal articles starting from year 2000 to present the various data mining techniques used in multiple customer based churn models. It then summarizes the existing telecom literature by highlighting the sample size used, churn variables employed and the findings of different DM techniques. Finally, we list the most popular techniques for churn prediction in telecom as decision trees, regression analysis and clustering, thereby providing a roadmap to new researchers to build upon novel churn management models.
Conference Paper
Full-text available
Customer churn is a major problem that is found in the telecommunications industry because it affects the company's revenue. At the time of the customer churn is taking place, the percentage of data that describes the customer churn is usually low. Unfortunately, the churn data is the data which have to be predicted earlier. The lack of data on customer churn led to the problem of imbalanced data. The imbalanced data caused difficulties in developing a good prediction model. This research applied a combination of sampling techniques and Weighted Random Forest (WRF) to improve the customer churn prediction model on a sample dataset from a telecommunication industry in Indonesia. WRF claimed can produce a prediction model which has a good performance on the imbalanced data problem. However, this research found that the performance of the prediction model developed by WRF using the dataset is still quite low. Sampling techniques were applied to overcome this problem. This research used the combination of simple under sampling and SMOTE. The result shown that the combined-sampling and WRF could produce a prediction model which had better performance than before.
Article
A model is proposed which expresses consumer satisfaction as a function of expectation and expectancy disconfirmation. Satisfaction, in turn, is believed to influence attitude change and purchase intention. Results from a two-stage field study support the scheme for consumers and nonconsumers of a flu inoculation.
Article
It is a generally acknowledged in marketing literature that pricing is a critical strategy that influences product/service demand and company profitability. Consequently, price plays an important role in influencing customers decisions in choosing and developing loyalty with a particular product or service. Moreover, consumers are becoming more value conscious, focusing on price and value as the primary reason when purchasing product and service. Thus, the influence of the multi-dimensions of perceived value on customer loyalty in the airline context was examined. In addition, the moderating effect of consumers price perception was also investigated in explaining service loyalty. The empirical findings strongly supported the significant impact of quality/emotional response/reputation, behavioral price on brand affect and brand trust. But no support was found for the hypothesized relationships between monetary price and brand affect and brand trust. Moreover, brand trust was found to significantly predict both attitudinal loyalty and behavioral loyalty, as hypothesized. Contrary to expectations, brand affect exerted no impact on both loyalty constructs. The moderating effect of price perception was significantly apparent solely on the relationship between brand affect and loyalty constructs.
Conference Paper
This paper will illustrate how to use data mining techniques to predict telecommunication customers churn. With a well analysis and interpretation of the data, valuable knowledge and key insights into the customers? needs can be achieved. A sample data based on customer usage was gathered, and different data mining techniques were applied over it. This paper?s contribution is to test the capability of a prediction data mining technique, which is the RULES Family algorithm-6 that has never been applied in such a case before. Two pre-stages techniques were applied before the prediction, which are the segmentation ?clustering? and the feature selection.
Article
This paper discusses the customer churning prediction problem in electronic commerce. In electronic commerce the customer data change is non-linear and time-varying and other characteristics, using a single prediction model to accurately predict e-commerce customer loss is difficult. In order to improve the prediction accuracy rate of electronic commerce churning, the model first uses the genetic algorithm for the screening of effecting factors, and extracts the important influence factors which affect the predicting results. Then support vector machine and neural network are respectively used to carry out the forecast. Finally, using support vector machine fuses the two prediction results to acquire the prediction results of the combination model. Simulation results show that the combined model can improve the prediction accuracy rate of the electronic commerce customer churning, and provides a new prediction method for the electronic commerce customer churning.
Article
The term “customer churn” is used in the industry of information and communication technology (ICT) to indicate those customers who are about to leave for a new competitor, or end their subscription. Predicting this behavior is very important for real life market and competition, and it is essential to manage it. In this paper, three hybrid models are investigated to develop an accurate and efficient churn prediction model. The three models are based on two phases; the clustering phase and the prediction phase. In the first phase, customer data is filtered. The second phase predicts the customer behavior. The first model investigates the k-means algorithm for data filtering, and Multilayer Perceptron Artificial Neural Networks (MLP-ANN) for prediction. The second model uses hierarchical clustering with MLP-ANN. The third one uses self organizing maps (SOM) with MLP-ANN. The three models are developed based on real data then the accuracy and churn rate values are calculated and compared. The comparison with the other models shows that the three hybrid models outperformed single common models.