Research project on customer sentiment index

A PROJECT REPORT ON
Framework to Model Customer Sentiment Index
for the Indian Broadband Industry
FOR
ACADEMIC RESEARCH
UNDER THE GUIDANCE OF
Dr. Sujata Joshi
Faculty (Marketing)
TOWARDS PARTIAL FULFILLMENT OF THE
REQUIREMENTS FOR THE AWARD OF
MASTER IN BUSINESS ADMINISTARTION IN TELECOM MANAGEMENT
SUBMITTED BY
ADITYA BASU
ARNAB MAJUMDAR
KRITI GUPTA
SANDEEPAN PAHARI
SUMIT GODIYAL
ARCHIT MALHOTRA
Symbiosis Institute of Telecom Management
Pune 412115
MBA TM (Batch 2012-14)

CERTIFICATE
This is to certify that project titled
Framework to Model Customer Sentiment Index for the
Indian Broadband Industry
Is a bonafide work carried out by
ADITYA BASU
ARNAB MAJUMDAR
KRITI GUPTA
SANDEEPAN PAHARI
SUMIT GODIYAL
ARCHIT MALHOTRA
Under the guidance of
Dr. Sujata Joshi
Faculty (Marketing)
Towards the partial fulfilment of
Master of Business Administration in Telecom Management
(MBA -TM)
____________ ____________
Director Project Guide

ACKNOWLEDGEMENT
“All I'm armed with is research.”
-- Mike Wallace
The 10 month research project as a part of curriculum at SITM lays a strong
foundation for aspiring managers like us not only by imparting quality, world class
education but also giving us an opportunity to get appropriate and worldwide
exposure before we take the actual step in.
We would like to express our deep gratitude to all those who gave us the knowledge
and requisite support to complete this report.
We are deeply indebted to our mentor Dr. Sujata Joshi whose help, stimulating
suggestions, knowledge, experience and encouragement helped us during all the time
of study and analysis of the project in the pre and post research period.
We would like to thank respected Director Sir Prof. Sunil Patil, Dy. Director Sir Prof.
Prasanna Kulkarni and all the faculty members of SITM for sharing their extensive
knowledge and expertise to equip us with the knowledge and skills to take on the
research.
We would also like to thank Dr. Sanjay Bhatia, Director Delivery Cross Group
Amdocs (India) and other Corporate Executives of Amdocs, without whose
valuable inputs this report was almost impossible.
ADITYA BASU
ARNAB MAJUMDAR
KRITI GUPTA
SANDEEPAN PAHARI
SUMIT GODIYAL
ARCHIT MALHOTRA

Research Project II Syndicate 10 II Broadband-CSI
PageA
ABSTRACT
FRAMEWORK TO MODEL CUSTOMER SENTIMENT INDEX FOR
THE INDIAN BROADBAND INDUSTRY
INTRODUCTION
Speed, coverage and stability of connection are the three major quality drivers for
broadband services. Broadband Internet (both fixed and mobile) being the key growth
segment in the communications market and quality being one of the key elements of
the customer’s experience, is critical to maximizing opportunities and moving away
from competing only on price. Nowadays, we can see that customer experience in
Broadband business is gaining momentum worldwide. Take O2 as an example – in
the UK, it has been advertising its Home Broadband Service as “Voted Number One
in Customer Satisfaction”. Accordingly, a majority of the broadband players are taking
steps to become more ‘customer-centric’ and put deeper customer insight at the heart
of their plans to provide more value
WHY CUSTOMER SENTIMENT?
The recent global economic downturn is putting further emphasis on the role of
customer experience management, in two ways. First, focusing more closely on
customers boosts operational efficiency, as better understanding of their needs allows
Broadband players to target investment and resources more precisely to match these
needs. Second, the Broadband players are recognizing that they need to focus more
on retention, to maximize the lifetime value of each customer. Indeed, a growing
number of players are resorting to minimizing customer churn by providing superior
customer experience as a means of capturing customers and strengthening loyalty.

PageB
Table of Contents
List of Figures..................................................................................................................... i
List of Tables......................................................................................................................ii
Abbreviations.....................................................................................................................iii
Project Title ....................................................................................................................... 1
Research Objective ........................................................................................................... 2
Executive Summary........................................................................................................... 3
Objective........................................................................................................................................3
Methodology..................................................................................................................................3
Key Findings & Conclusion.........................................................................................................4
1 INTRODUCTION........................................................................................................ 5
1.1 Skeletal Background........................................................................................................5
1.1.1 Framework Problem & Aim.....................................................................................5
1.2 Reasons to focus on the Broadband industry..............................................................6
1.3 Cascading impact of mobile broadband services........................................................7
1.4 Introduction to Broadband-CSI framework...................................................................7
2 LITERATURE REVIEW .............................................................................................. 8
2.1 Review & Study ................................................................................................................8
2.1.1 Customer Sentiment ................................................................................................8
2.1.2 Why Consumer Sentiment Matters........................................................................8
2.1.3 How Consumer Sentiment is used?......................................................................9
2.1.4 What Composes Consumer Sentiment.................................................................9
2.1.5 Amdocs Customer Experience Index (ACEI).......................................................9
2.1.6 Survival Model ........................................................................................................10
2.1.7 Objectives of survival analysis .............................................................................11
2.1.8 KANO’s Model ........................................................................................................12
3 RESEARCH METHODOLOGY ................................................................................ 14
3.1 Customer Life-Cycle of a Broadband Customer........................................................14
3.2 Research Approach .......................................................................................................14
3.2.1 Methodology............................................................................................................14
3.2.2 Sampling Plan & Demographics ..........................................................................15
3.3 Research Instrument......................................................................................................16
3.3.1 Conceptual Framework & Measurement Model ................................................16
3.4 Statistical Construct .......................................................................................................17
3.4.1 Statistical Analysis..................................................................................................17

PageC
3.4.2 Application of Models.............................................................................................17
4 LIMITATIONS OF THE PROJECT ........................................................................... 18
5 DETAILED ANLAYSIS & INTERPRETATION .......................................................... 19
5.1 Data Reliability & Validity ..............................................................................................19
5.1.1 Scale Reliability Test: ............................................................................................19
5.1.2 KMO & Bartlett’s Test:...........................................................................................19
5.1.3 Factor Analysis: ......................................................................................................20
5.2 Detailed Findings............................................................................................................21
5.2.1 Broadband CSI Scores & the overall performance...........................................21
5.2.2 Key focus areas – Importance Performance Plot..............................................21
5.2.3 Analysis of Customer Behaviour..........................................................................22
5.2.4 Survival Model ........................................................................................................24
5.2.5 Segmentation Study (Analysis of Parameters & Attributes)............................26
5.2.6 Segmentation Study (Customer Analysis)..........................................................27
5.3 Key Findings from the Analytical Construct ...............................................................28
6 RECOMMENDATIONS & DISCUSSIONS................................................................ 30
6.1 Conclusions & Discussions...........................................................................................30
6.2 Recommendations .........................................................................................................31
6.2.1 Advancement on the path.....................................................................................31
6.2.2 Recommendations .................................................................................................31
Annexures/Appendix ......................................................................................................... a
References:-...................................................................................................................... d
Websites:- .......................................................................................................................... f

Pagei
LIST OF FIGURES
Figure 1: Broadband subscribers in India, by technology, September 2012 [Source:
TRAI, Analysys Mason, 2013] .........................................................................................................6
Figure 2: Survival-Event Analysis Plot.......................................................................................10
Figure 3: KANO's Model Depiction..............................................................................................12
Figure 4 (Customer Life Cycle).....................................................................................................14
Figure 5:Research Plan..................................................................................................................15
Figure 6: Population Sample.........................................................................................................15
Figure 7: Sample Demographics..................................................................................................15
Figure 8: Conceptual-Model..........................................................................................................16
Figure 9: Importance of Attributes & Touch-Points................................................................20
Figure 10: Overall CSI Scores.......................................................................................................21
Figure 11: Overall IP-Plot...............................................................................................................21
Figure 12: Churn Model Depiction...............................................................................................23
Figure 13: Hazard Plot (Churn).....................................................................................................25
Figure 14: Hazard Plot (Customer Category)............................................................................25
Figure 15: Parameter Categories.................................................................................................26
Figure 16 : Customer Categories.................................................................................................27
Figure 17: Customer Sentiment Drivers ....................................................................................30
Figure 18: Improving Broadband Customer Sentiment.........................................................31

Pageii
LIST OF TABLES
Table 1 (Statistical Methods).........................................................................................................17
Table 2 (Statistical Models) ...........................................................................................................17
Table 3 (Effect of CSI on Business Perspectives) .......................................................... 22
Table 4 (CSI-Business Drivers) ....................................................................................................22
Table 5 (Descriptives for Survival Model)..................................................................................24
Table 6 (Model Verification)...........................................................................................................24
Table 7 (Concluding Statements) ................................................................................................30

Pageiii
ABBREVIATIONS
ACEI - Amdocs Customer Experience Index
BB - Broadband
WOM - Word of Mouth
BB-CSI - Broadband Customer Sentiment Index
HW/Rtd. - Housewives & Retired Personnel
Gen-X - Generation X
Gen-Y - Generation Y
SP - Service Provider

Page1
PROJECT TITLE
FRAMEWORK TO MODEL CUSTOMER SENTIMENT INDEX
FOR THE INDIAN BROADBAND INDUSTRY

Page2
RESEARCH OBJECTIVE
 Build a framework to measure Consumer Sentiment Index for Indian
Broadband industry using the ACEI Model of Amdocs
 The framework will:
 Consider customer life-cycle touch-points for a Broadband customer
 Identify & define the relationships between Key determinants of the
Broadband services
 Use ACEI Model as the baseline towards the Indian Broadband Industry
 Help understand customer behavior, their intention to spend, intent to
recommend, usage of interactive service, intent to change operator etc.
 Help understand key business drivers & their impact on service delivery
 Demarcate target customer segments for future strategic decisions

Page3
EXECUTIVE SUMMARY
Broadband in India has historically been associated with fixed technologies, and for
this reason penetration has always been limited to the major cities and towns. Fixed
broadband (FBB) household penetration in India stood at around 7% in 2012,
representing about 15 million subscribers, of which around 85% were DSL
subscribers. Another 16–18 million broadband subscribers can be added to this total
if large-screen mobile broadband subscribers are included, which are currently driven
by EV-DO. However, the largest potential lies in the small-screen mobile broadband
market, which is currently limited to 18–20 million 3G subscribers.
OBJECTIVE
The objective of the research is to implement the ACEI Model of AMDOCS that can
measure customer sentiment in the Indian Broadband Industry. ACEI effectively
measures Product (features, quality, and uniqueness), Price compared to acceptable
alternatives, Competitive environment. The emotional connection to the brand and its
products, Prior “goodwill” established through previous interactions and other
internal/external factors. The Broadband-CSI framework will attempt to provide a
reliable industry benchmark & give a cumulative measure, of customer experience
index across various touch-points & service parameters throughout the customer life-
cycle.
METHODOLOGY
The ACEI Measurement model is the Key instrument for the research. The details from
Broadband service providers are a key input to the model. The data was collected
from both primary & secondary sources. A pre-pilot survey was conducted in Pune.
For validation of data, the following was conducted scale reliability test, various
statistics. Data interpretation was done which would help in formulating strategic
decisions.

Page4
KEY FINDINGS & CONCLUSION
Some of the Key Findings from the analysis include the following:
 Average Broadband-CSI across population sample is 6.66 on a scale of 10.
 Housewives & Retired have the lowest CSI.
 Attributes such as Advertisements & Promotions, Dealer’s access, Experience at
outlets & Relocation services do not play an important role.
 Service expectations of Managers are very high.
 Overall impact of a unit increase in ACEI suggests a 1.53 times increase in intent
to purchase more.
Effective customer service involves meeting or exceeding customer needs. However,
customer service is not just about what you do for your customers, it also concerns
how the service is carried out.
Customer Experience Management is not, an old idea in a new wrapper. In recent
years a number of fundamental changes have occurred in the business environment.
The changes have been fuelled by technological advancements, which have
expanded the range of services available to customers, and simultaneously led to
escalating customer expectations. Broadband CSI framework provides a solution
to bridge the gap between customer experience perception & management
perception of the customer, being helpful to both parties at the same time.

Page5
1 INTRODUCTION
1.1 SKELETAL BACKGROUND
The aim of this research is to build a framework that explains the relationship between
customer sentiments, retention and loyalty based on service attribute performance in
Broadband industry. Customer behavior plays an important role towards business
performance. The service value chain links service quality, customer actions &
business profitability. The value of service quality influences customer retention i.e.
linked to repurchase intentions; cross sale & loyalty towards the brand i.e. linked to
word of mouth & referral intent. Understanding customer sentiment by providing
superior customer experience holds a key context in this research.
1.1.1 Framework Problem & Aim
The research questions that can be answered through this analysis are:-
What is the life-cycle of the Broadband customer?
How service attributes influence customer experience?
What is the relationship between service attribute importance & performance?
How is customer experience linked to customer lifetime value & churning?
What business terms are responsible for retention; loyalty; word of mouth; switching
probability?
The aim is to implement the ACEI Model that can measure customer sentiment in the
Indian Broadband Industry with the following objectives:-
 Measure customer sentiment by analyzing the Indian consumer behavior
pattern by conducting a pre-pilot survey in Pune
 Study the determinants which contribute to the customer experience
 Understand the customer perspective, retention & loyalty behavior

Page6
1.2 REASONS TO FOCUS ON THE BROADBAND INDUSTRY
Broadband in India has historically been associated with fixed technologies, and for
this reason penetration has always been limited to the major cities and towns. Fixed
broadband (FBB) household penetration in India stood at around 7% in 2012,
representing about 15 million subscribers, of which around 85% were DSL
subscribers. Another 16–18 million broadband subscribers can be added to this total
if large-screen mobile
broadband subscribers are
included, which are currently
driven by EV-DO. However,
the largest potential lies in the
small-screen mobile
broadband market, which is
currently limited to 18–20
million 3G subscribers.
We expect the overall broadband mix in India to change during the next five years as
a number of changes take place both on the wireless and fixed sides. FBB will be a
niche technology within the home broadband market and will largely be driven by the
cable digitization process as cable broadband technology emerges. We expect the
number of large-screen wireless subscribers to triple during the next 4–5 years, driven
by EV-DO and the emergence of LTE technology. LTE will have a major role to play
in the long run with the availability of 700MHz spectrum by 2015. Most of the take-up
will be driven by 3G small-screen mobile broadband, which we expect to increase
rapidly from 2014 to 2015 as smartphones become more affordable and data pricing
issues are resolved. The main stakeholders in the supply side are the broadband
service providers. In the National Telecom Policy 2012 (NTP 2012), the government
laid out an ambitious target of 600 million broadband subscribers in total by 2020.
Figure 1: Broadband subscribers in India, by technology,
September 2012 [Source: TRAI, Analysys Mason, 2013]

Page7
1.3 CASCADING IMPACT OF MOBILE BROADBAND SERVICES
 Mobile broadband services will generate incremental revenue of Rs.940 Bn in 2015
for telecom industry as a whole, constituting roughly 1.5% of India’s real projected
GDP in 2015.
 Incremental 3G data revenue for mobile operators is expected to cross Rs. 67 Bn
in 2015 growing at a CAGR of 109 percent over the next 5 years.
 Revenue from 3G related data services for other VAS value chain players is likely
to reach Rs.36 Bn in 2015.
 3G handset sales are expected to stand at approximately 135 Mn in 2015.
Revenues from 3G handset sales are expected to reach Rs.670 Bn in 2015
growing at a CAGR of 33% between 2011 and 2015.
 Equipment manufacturer revenue from 3G roll out is expected to be Rs.165 Bn in
2015 growing at a CAGR of 72% over the next 5 year period.
 Cumulative investment related to 3G is expected to be in the region of Rs 500 Bn
for the period of 2010-15.
1.4 INTRODUCTION TO BROADBAND-CSI FRAMEWORK
Customer sentiment Index is a cumulative measure of importance and experience
across all the interactions. These interactions, in a customer life cycle, are through
various service parameters.
 The various touch-points considered are:-
o Brand Image
o Installation Experience
o Usage Experience
o Experience Centers
o Customer Care Experience
o Billing Experience
 Based on the customer life-cycle, a comprehensive questionnaire was
developed and pre-pilot survey was conducted in Pune.
 The attitude of a customer that is created due to an interaction between
broadband service provider and a customer as perceived through a customer’s
mindset during the lifecycle is the Customer sentiment index

Page8
2 LITERATURE REVIEW
This segment of the report is a review of the literature supporting the research
objectives. The study focuses on the building & extension of ACEI model of Amdocs,
which would support corporate decision making. The chapter clearly defines the
statistics & models applied for the completion of the research.
2.1 REVIEW & STUDY
2.1.1 Customer Sentiment
It is a statistical measure and economic indicator of the overall health of the economy
as determined by consumer opinion. Consumer sentiment takes into account an
individual's feelings toward his or her own current financial health, the health of the
economy in the short term and the prospects for longer term economic growth.
Consumer sentiment indexes, also known as consumer confidence indexes, are
reports on the degree of optimism that consumers have about the overall state of the
economy, as well as their personal financial situation and its stability. This is used by
a large number of banks, corporations and governmental entities to plan policy on a
month-to-month basis.
2.1.2 Why Consumer Sentiment Matters
Consumer sentiment is considered important due to the fact that the level of
confidence that consumers have about the stability of their incomes can be used to
understand the overall trend of the economy. If consumer confidence is lower,
consumers will spend less money, save more and cause the economy to shrink. If
consumer confidence is higher, consumers will spend more, save less and cause the
economy to expand. This can also be used to examine trends about which way the
economy is heading, as opposed to single points of data. This was described by John
Maynard Keynes as "animal spirits," due to the fact that at the largest scale consumers
cannot be considered to be rational actors.

Page9
2.1.3 How Consumer Sentiment is used?
Consumer sentiment is used by a wide range of investors, businesses, banks and
governmental organizations to plan their month-to-month and longer term actions. By
examining the willingness of consumers to spend money, companies and investors
can gauge the likelihood of selling product and adjust operations and investments
accordingly. The government can choose to reduce or increase tax revenue. Banks
can charge lower or higher interests depending on how much consumers are going to
want to save versus how much they will want to take out loans.
2.1.4 What Composes Consumer Sentiment
Consumer sentiment indexes examine three things. The first thing examined is how
consumers feel about their current financial situation. This will influence smaller
purchases and their day-to-day life, affecting purchases like food and various luxuries.
The second is about the state of the economy as a whole, which will affect their
likelihood to save money against the future. The third is about their long-term financial
situation, which works with their view on the state of the economy about saving money,
in addition to helping determine whether they are likely to make major purchases.
2.1.5 Amdocs Customer Experience Index (ACEI)
“It is becoming increasingly clear to communication service providers that delivering
best in class customer experience is a competitive differentiator. It drives customer
loyalty, and directly impacts revenue and profitability. ”
Anshoo Gaur, President & Head, AMDOCS (India)
The ACEI measures customer experience on a scale of 1 to 10. ACEI can be deployed
across various lines of businesses & demographics.
The ACEI model considers the following aspects and creates a framework to analyze
key determinants across various stages of customer life-cycle:-
Experience parameters: - Brand Image, Installation Experience, Usage Experience,
Gallery/Store experience, Customer Care Experience, Billing Experience
Segmentation parameters: - Gender, Age group, Members in family, monthly income,
Occupation, Education, Time of Usage
Behavioral parameters: - Propensity to recommend, Propensity to churn, Propensity
to spend more, Frequency and type of complaints, Other services used

Page10
The analytical construct clearly outlines the index value & correlations amongst
various touch points & service attributes.
2.1.6 Survival Model
Survival analysis is generally defined as a set of methods for analyzing data where the
outcome variable is the time until the occurrence of an event of interest. The event can
be death, occurrence of a disease, marriage, divorce, etc. The time to event or survival
time can be measured in days, weeks, years, etc. For example, if the event of interest
is heart attack, then the survival time can be the time in years until a person develops
a heart attack.
In survival analysis, subjects are usually followed over a specified time period and the
focus is on the time at which the event of interest occurs. Why not use linear regression
to model the survival time as a function of a set of predictor variables? First, survival
times are typically positive numbers; ordinary linear regression may not be the best
choice unless these times are
first transformed in a way that
removes this restriction. Second,
and more importantly, ordinary
linear regression cannot
effectively handle the censoring
of observations.
Unlike ordinary regression
models, survival methods
correctly incorporate information
from both censored and uncensored observations in estimating important model
parameters. The dependent variable in survival analysis is composed of two parts:
one is the time to event and the other is the event status, which records if the event of
interest occurred or not. One can then estimate two functions that are dependent on
time, the survival and hazard functions. The survival and hazard functions are key
concepts in survival analysis for describing the distribution of event times. The survival
function gives, for every time, the probability of surviving (or not experiencing the
event) up to that time. The hazard function gives the potential that the event will occur,
per time unit, given that an individual has survived up to the specified time. While these
Figure 2: Survival-Event Analysis Plot

Page11
are often of direct interest, many other quantities of interest (e.g., median survival)
may subsequently be estimated from knowing either the hazard or survival function
Methods include parametric, nonparametric and semi parametric approaches:
Parametric methods assume that the underlying distribution of the survival times
follows certain known probability distributions. Popular ones include the exponential,
Weibull, and lognormal distributions. The description of the distribution of the survival
times and the change in their distribution as a function of predictors is of interest. Model
parameters in these settings are usually estimated using an appropriate modification
of maximum likelihood.
A nonparametric estimator of the survival function, the Kaplan Meier method is widely
used to estimate and graph survival probabilities as a function of time. It can be used
to obtain univariate descriptive statistics for survival data, including the median survival
time, and compare the survival experience for two or more groups of subjects. To test
for overall differences between estimated survival curves of two or more groups of
subjects, such as males versus females, or treated versus untreated (control) groups,
several tests are available, including the log-rank test. This can be motivated as a type
of chi-square test, a widely used test in practice, and in reality is a method for
comparing the Kaplan-Meier curves estimated for each group of subjects.
2.1.7 Objectives of survival analysis
 Estimate time-to-event for a group of individuals
 To compare time-to-event between two or more groups
 To assess the relationship of co-variables to time-to-event
Note: expected time-to-event = 1/incidence rate

Page12
2.1.8 KANO’s Model
The Kano model of customer satisfaction is a useful tool to classify and prioritize
customer needs based on how they affect customer’s satisfaction (Kano et al., 1984).
It captures the nonlinear relationship between product performance and customer
satisfaction.
The Kano Model of Customer satisfaction divides product attributes into three
categories:
1) Threshold Attributes
Threshold (or basic) attributes
are the expected attributes or
“musts” of a product, and do not
provide an opportunity for
product differentiation.
Increasing the performance of
these attributes provides
diminishing returns in terms of
customer satisfaction; however
the absence or poor performance of these attributes results in extreme customer
dissatisfaction.
2) Performance Attributes
Result in customer satisfaction when fulfilled and dissatisfaction when not fulfilled.
Performance attributes are those for which more is generally better, and will improve
customer satisfaction. Conversely, an absent or weak performance attribute reduces
customer satisfaction. Of the needs customers verbalise, most will fall into the
category of performance attributes. These attributes will form the weighted needs
against which product concepts will be evaluated. The price for which customer is
willing to pay for a product is closely tied to performance attributes.
3) Attractive attributes (Excitement)
Excitement attributes are unspoken and unexpected by customers but can result in
high levels of customer satisfaction, however their absence does not lead to
Figure 3: KANO's Model Depiction

Page13
dissatisfaction. Excitement attributes often satisfy latent needs – real needs of which
customers are currently unaware. In a competitive marketplace where manufacturers’
products provide similar performance, providing excitement attributes that address
“unknown needs” can provide a competitive advantage.
KANO’s Model (Customer Satisfaction Loyalty Grid)
Segments the customers into four broad categories:-
 Champions: - Highly satisfied and loyal, these customers are very likely to
return for the service purchase.
 Switchers: - Frequent casual customers but they are equally likely to visit a
competitor that provides a similar service, perhaps with better value.
 Captives: - Most puzzling of the customers for executives to grasp. They have
lower-than-average utility satisfaction scores, but are highly loyal to the firm
 Antagonist: - These people probably had a bad experience with the service.
Satisfaction is defined as a measure of how services supplied by a company meet or
surpass the customer expectation. Satisfaction score is the Individual ACEI score for
a particular customer.
Customer loyalty is all about attracting the right customer, getting them to buy, buy
often, buy in higher quantities and bring you even more customers. A quantitative
measure of intent to spend, intent to recommend, & individual customer experience
results in customer loyalty score. Higher the loyalty score, higher is the intent to spend
& recommend.

Page14
3 RESEARCH METHODOLOGY
This chapter of the report presents the approach towards the conduct of the research
& building of the framework. It explains the details about the data sources; the
methodology; the research instrument; the sampling plan & the relevant mathematical
techniques involved relevant to the customer life-cycle of a Broadband consumer.
3.1 CUSTOMER LIFE-CYCLE OF A BROADBAND CUSTOMER
Figure 4
:Customer Life
Cycle
3.2 RESEARCH APPROACH
3.2.1 Methodology
 Focus Segment for the study were Broadband customers
 25 parameters were brainstormed as part of the Pre-Pilot study based on
quantitative & qualitative analysis
 Questionnaire was developed in accordance to the parameters
 The study captured both importance & experience levels across the 25
parameters. Behavioural & segmentation parameters were also captured.
 Various statistical tools & analysis ranging from scale reliability to factor
analysis to regressions & model application were considered
 The one to one & online survey was conducted in Pune city
Customer
Acquire
Serve
Grow
Retain
Brand Image
Awareness
Need for BB
Store/ Gallery Experience
Brand Choice Customer care
experience
Billing experience
Usage experience
Word of Mouth
Installation experience

Page15
Figure 5: Research Plan
3.2.2 Sampling Plan & Demographics
Over 220 people were surveyed in Pune. The sampling plan was devised towards the
adequate representation of the statistical construct.
Figure 6: Population Sample
Figure 7: Sample Demographics
Shortlisted Parameter
• 25 parameters were
shortlisted after
brainstorming and
discussions
Questionnaire
Preparation
•Questions were formed
based on the 25
parameters and the
customer lifecycle.
Pre-Pilot Survey
Conducted
•Pre-Pilot Survey was
conducted on 221
people
Pre-Pilot Data Validation
and analysis
•Validation done by
•Scale Reliability Test
•Various Statistics
221
142
79
100 96
25
0
50
100
150
200
250
Male Female <15-24 yrs 25-35 yrs > 36 yrs
Total Gender Age-Group
Sample Demographics
Emp/
Exec
HW/
Rtd.
Large
Buss.
Man
ager
Profs
/Self
Emp
Small
Buss.
Stud
ent
Othe
rs
Occupation 69 15 5 15 25 12 75 5
69
15
5
15
25
12
75
5
0
10
20
30
40
50
60
70
80
Occupation
<Rs.3000
, 46, 21%
Rs.3000-
6000, 8,
4%
Rs.6000-
15000,
15, 7%
Rs.15K-
30K, 51,
23%
Rs.30K-
50K, 51,
23%
Rs.50K-
80K, 30,
13%
>Rs.8000
0, 20, 9%
MONTHLY INCOME

Page16
3.3 RESEARCH INSTRUMENT
Our research gadget was the AMDOCS customer experience index framework. The
design of the model facilitated to construct the Broadband-CSI structure.
3.3.1 Conceptual Framework & Measurement Model
Figure 8: Conceptual-Model
The customer experience index is calculated using the weighted average method
which aptly quantifies the combination of importance & performance. The formula for
A represents the weighted average formula. Finally the customer experience index is
calculated on a 10 point scale using the equation CEI=1.5Ai – 0.5.
The framework provides a multi-dimensional view of Customer Experience and its
impact. It helps discover how Experience affects Customer behavior. How well can it
drive customers to spend more and recommend.

Page17
3.4 STATISTICAL CONSTRUCT
The statistical tools, methods & application of models helped us in the following:-
 Analysis of touch-points & attributes
 Analysis of customer behaviour
 Study of Business Drivers
 Customer segmentation analysis
 Parameter segmentation analysis
3.4.1 Statistical Analysis
Reliability Test-
Cronbach’s Test
Cronbach alpha coefficient is an indicator of internal
consistency of the scale
KMO Test-Feasibility of
Factor Analysis
The KMO statistic is to check the consistency & correlation
in the parameters of the questionnaire
Factor Analysis
Factor Analysis to confirm the already identified factors in
the questionnaire & to rename buckets if necessary
Analysis of Segments
Considered
Analysis of various segmentation parameters
Importance Performance
Analysis
To analyze & recommend key focus areas for service
providers
Binary Logistic
Regression
Relationship or correlation of parameters with the changes
in ACEI score
Regression Analysis Check the validity & fitness of model
Table 1 (Statistical Methods)
3.4.2 Application of Models
KANO’s Model
(Satisfaction-Loyalty Grid)
Customer Segmentation (Satisfaction Loyalty Grid)
Attribute Segmentation (Basic; Performance; Exciting)
Survival Modelling Understanding Customer Life Time Value & Churn
Analysis of Segments
Considered
Analysis of various Customer Segments on the basis of
Loyalty & Profitability
Table 2 (Statistical Models)

Page18
4 LIMITATIONS OF THE PROJECT
1) Sample size -- The number of the units of analysis was small. Open to more
advanced & wider data collection. Significant relationships from the data, would
be more accurate in terms of attributes & touch-points.
2) Availability of data -- Reliable & sufficient data from the broadband providers
will give a more clear understanding of the trends in the services & experiences.
3) Limited Demographics -- The study was limited to students, professional &
employees, an increase in sample size & varied demographics would provide
a more heterogeneous sample.
4) Positive Limit -- The time of study & research is always an obstacle always
more is wanted; it opens doors for understanding wider aspects & the futuristic
application & interpretation of data.

Page19
5 DETAILED ANLAYSIS & INTERPRETATION
This segment of the report deals with data validity & reliability tests. It also presents
the empirical analysis, in terms of various relationships between service quality &
customer behaviours in the Indian broadband industry. The chapter discusses the
interrelationships using various statistical & analytical methods; to quote a few are the
importance-performance analysis, survival model; the Kano’s implementation & a few
more. The association between sentiment, loyalty, and retention of a broadband
customer is analysed as a part of this study.
5.1 DATA RELIABILITY & VALIDITY
5.1.1 Scale Reliability Test:
 To verify that a 7-pt scale is reliable and sufficient for obtaining the desired
results. Reliability test is done with the help of Cronbach Alpha coefficient. The
Cronbach alpha coefficient is an indicator of internal consistency of the scale.
 Using the SPSS tool it was found that the Cronbach Alpha for the Importance
Scale is 0.967, where as it is 0.974 for Experience Scale. This indicates very
good reliability of the scale.
5.1.2 KMO & Bartlett’s Test:
 KMO & Bartlett’s statistic of 0.935 indicates excellent sampling adequacy and
significant correlations between the questions in the questionnaire.
 Identification of different factors which influence the Customer Sentiment Index.
 Also important parameters were identified within the factors depending on their
loading on a particular question.

Page20
5.1.3 Factor Analysis:
It is done to analyze parameter
grouping: To understand how
respondents are correlating the
questions in the questionnaire. The
parameters and questions were
grouped as per the customer lifecycle
flow, verify if the questions are required
to be set in a different order. Evaluate
the primary data for Market research
methodology and prevention against
data fudging.
The study considered all the touch-
points of the broadband customer life-
cycle. The 25 key parameters were
grouped & ranked on the basis of their
impact on the CSI using the Factor
Analysis statistical technique.
Customer Service is likely to have the
highest impact on the CSI, followed by
usage experience. The top two
experience parameters in both cases
involve, customer helpline easy access,
efficient resolution of queries &
complaints; Wi-Fi connectivity,
Continued Service in heavy rains
respectively.
Figure 9: Importance of Attributes & Touch-Points
Customer Service
 Customer Helpline
easy Access
 Efficient resolution
of queries
 Repair Options
 Courteous Staff
 Outlet Experience
 Interactive Website
 Dealer Access
Usage Experience
 Wi-Fi Connectivity
 Continued Service
 Download Speed
 Experience of
Change
Brand Image
 Promotions
 Advertisements
 Relocation
Experience
Installation &
Service
Experience
 Regular Payment
Alerts
 Recharge Flexibility
 Behavior of
Installation Staff
Brand Offerings
 Valued Customer
 Variety Packages
 Trustworthiness
Assurance &
Billing Experience
 Plans & Offers
 Valued Pricing
 Accurate Billing
 First-Time
Activation
1
5 6
3 4
2
1
2
2
2
2
2
2
1
1
1
1
1

Page21
5.2 DETAILED FINDINGS
5.2.1 Broadband CSI Scores & the overall performance
 Average CSI Score stands at 6.66 on a scale of 10
 The maximum average CSI was observed for the managers & high spenders
category
 The minimum average Broadband-CSI was observed for Housewives/Retired
personnel i.e. 5.33 on a scale of 10
 The CSI scores lay very close to the population average of 6.66
5.2.2 Key focus areas – Importance Performance Plot
Figure 11: Overall IP-Plot
Advertisements
Promotions
Plans & offers
Pricing is value
Trustworthy operator
Variety of Packages
I feel valued customer
First time installation
Activation of first time
services
Behavior of installation
staff
Download Speed
Continued Service in
heavy rains
Wifi Connectivity
Experience in Relocation
of services
Experience of change in
service
Dealers are widely
spread
Experience at…
Interactive website
Customer Helpline easy
Acccess
Helpline staff are…
Queries solved
efficiently & quickly
Maintenance & Repair
optiions
Accurate (Fair) Charge
deduction
Regular payment alerts
Recharge Flexibility
4.30
4.40
4.50
4.60
4.70
4.80
4.90
5.00
5.10
5.20
5.30
4.70 4.80 4.90 5.00 5.10 5.20 5.30 5.40 5.50 5.60 5.70
PERFORMANCE
IMPORTANCE
IP-Plot
Figure 10: Overall CSI Scores
Gen X Gen Y
Low
Spend
Med
Spend
High
Spend
Emp/
Exec
HW/R
td
Large
Busin
ess
Mana
ger
Prof/
Self
Emp
Small
Busin
ess
Stude
nt
BB-CSI Score 6.64 6.81 6.35 6.86 6.97 6.85 5.33 6.74 8.03 6.36 6.24 6.64
Overall ACEI 6.66 6.66 6.66 6.66 6.66 6.66 6.66 6.66 6.66 6.66 6.66 6.66
6.64 6.81
6.35
6.86 6.97 6.85
5.33
6.74
8.03
6.36 6.24
6.64
0.00
1.00
2.00
3.00
4.00
5.00
6.00
7.00
8.00
9.00

Page22
 Focus Areas: Trustworthiness, Continued Service, Maintenance & Repair
Options, Efficient resolution of complaints.
 Attributes such as Advertisements & Promotions, Dealer’s accessibility,
Experience at outlets & Relocation services do not play an important role.
5.2.3 Analysis of Customer Behaviour
5.2.3.1 Impact of CSI on the key business drivers
A unit change brought about in the Customer sentiment depicts the following
changes:
Customer
Segment
Chances of
recommendation
Purchase
More
Customer
Churn
Spend more for
better services
Complaints
raised
Overall 1.61times 1.53 times -0.22 times 1.02 times -0.13 times
Gen-X 1.68 times 1.56 times -0.21 times 1.060 times -0.18 times
Gen-Y 1.26 times 1.45 times -0.35 times -0.5 times -.34 times
Low Spend 1.63 times 1.67 times -0.31 times 1.14 times -.19 times
Med Spend 1.45 times 1.42 times -0.03 times -0.03 times -0.22 times
High Spend 30 times 1.78 times -0.43 times -0.24 times -0.18 times
Table 3 (Effect of CSI on Business Perspectives)
A unit increase in BB-CSI results in
 0.13 times less complaints
 0.22 times less customer churn
 1.02 times increased spend intent
 1.61 times increased recommend intent
 1.53 times increased purchase intent
KEY BUSINESS DRIVERS
Unit Increase in BB-CSI Opportunity/Effects
Increase in Positive Publicity
Higher Satisfaction Scores
More Revenue Opportunities
Less Customer Care Cost
More Send for services
Chances of Recommendation
Less Customer Churn
Spend More for better services
Less complaints raised
Purchase more services
Table 4 (CSI-Business Drivers)

Page23
5.2.3.2 Churn Model
The charts above show a distinct pattern 29% of the population sample have switched
in the past. 22% of the sample is planning to switch. The primary reasons for churn
are:
 Better services & offers by the other broadband providers (51% of the sample)
 Overall bad service experience (23% customers)
 Relocation service experience is not worth customer’s trust (14% customers)
For attaining higher customer sentiments & experience these overall areas need to
be focussed upon.
5.2.3.3 Complaint Analysis:
The top 3 complaint areas include (54% of sample)
 Speed issues (77 respondents approx. 35% of the sample)
 Billing & Recharge issues (21 respondents approx. 10 % of sample)
 Activation & Deactivation issues (21 respondents approx. 10 % of the sample)
Yes,
63,
29%
No,
158,
71%
Switched in the Past
Bad
Experience,
13, 20%
For
Better
Services
/Offers,
24, 37%
Price, 5,
8%
Moving
to Other
Location
, 17,
27%
Others
, 5, 8%
Reason to Switch
Good
Experien
ce, 51,
23%
No better offers by
other operators, 57,
26%Others,
41, 18%
No
Respons
e, 72,
33%
Reason Not to Switch
Yes,
49,
22%
No,
172,
78%
Planning to Change
Good
Experien
ce, 78,
35%
No better offers by
other operators, 63,
29%
Others,
20, 9%
No
Response,
60, 27%
Reason Not to Change
Bad
Experie
nce, 11,
23%
For
Better
Services
/Offers,
25, 51%
Price, 5,
10%
Moving
to Other
Location
, 7, 14%
Others,
1, 2%
Reason to Change
Figure 12: Churn Model Depiction

Page24
5.2.4 Survival Model
5.2.4.1 Descriptive Statistics
Tells us that total events to be analyzed are 54. The censored number of cases are
116 that is these customers have not churned.
Cases excluded due to missing values are 51.
The 54 cases analyzed are obtained from all the customer categories i.e., switchers,
antagonists, captives and champions.
Case Processing Summary
N Percent
Cases available in analysis
Eventa
54 24.4%
Censored 116 52.5%
Total 170 76.9%
Cases dropped
Cases with missing values 51 23.1%
Cases with negative time 0 0.0%
Censored cases before the
earliest event in a stratum
0 0.0%
Total 51 23.1%
Total 221 100.0%
a. Dependent Variable: Code_From_when_using_Current_Provider
Table 5 (Descriptives for Survival Model)
5.2.4.2 Omnibus test of model coefficients
Table 6 (Model Verification)
Tells us how well is the model build and how will it perform. Here we are analyzing
survival on the basis of the customer categories i.e. the captives, switchers,
antagonists and champions. We need to check how customer categories or custcat
contributes to the model.
The change from previous step and change from previous block both report the effect
of adding custcat to the model selected in Block 1. Since the significance value of the
change is less than 0.05, you can be confident that custcat contributes to the model.

Page25
5.2.4.3 Survival Functions
Data captured tells us the following:
The survival curve shows that after
the tenure of code 2 (months of
service) a lot of customers tend to
churn out due to many reasons. This
is the time when churning actually
starts to happen. That is way the
graph starts becoming blocky. The
block size is also huge. So a lot of
customers (54 in number) have
shown tendencies to churn out after
this time. This behavior is continued
henceforth.
Here survival pattern show that
antagonists are the ones who are
actually churning out in the previous
mentioned pattern. The focus is to
move the antagonists & Switchers to
the Champions categories by
understanding the customer’s
sentiment needs & delivering aptly on
the same.
Figure 13: Hazard Plot (Churn)
Figure 14: Hazard Plot (Customer Category)

Page26
5.2.5 Segmentation Study (Analysis of Parameters & Attributes)
5.2.5.1 KANO’s Quadrants – Parameter Analysis
 The Basic or Must Be Attributes:- Wi-Fi Connectivity; Activation of First time
services; valued pricing; trustworthiness & Regular Payment Alerts
 The population is satisfied with the Performance Attributes:- Recharge
Flexibility; Download Speed; Continued Service; Plans & Offers; Maintenance &
Repair Options; Efficient resolution of complaints & Behavior of Installation Staff.
These are key Drivers of Broadband service
Figure 15: Parameter Categories
 The Delight parameters frame includes Advertisement & Promotions; Value to
the customers & First-time installation services.
 Must be category should be catered & improved to reach Key Driver Category else
will result into dissatisfaction.

Page27
5.2.6 Segmentation Study (Customer Analysis)
5.2.6.1 Satisfaction Loyalty Grid: Descriptive
Analysis:
 The following categories of customers are
Switchers (13%), Antagonists (28%),
Champions (41%), and Captives (18%).
 Champions are the highly satisfied-highly loyal
category of people.
 Switchers are highly satisfied but not highly
loyal. Need to be pulled to the champions category. Focus should be on winning
loyalty.
 Captives are highly loyal but not highly satisfied. By providing those with better
experience can be pulled to the champions category.
Figure 16 : Customer Categories
Switchers,
30, 13%
Antagonist
s, 61, 28%
Champions,
91, 41%
Captives
, 39,
18%
Customer Categories

Page28
5.3 KEY FINDINGS FROM THE ANALYTICAL CONSTRUCT
1) Referral Tendency
“Unit increase in Broadband-CSI
increases referral tendency by 1.61
times”
 Focus Areas: Trustworthiness,
Continued Service, Maintenance
Options, Efficient resolution of
queries, Valued customer relation.
 Attributes such as Advertisements
& Promotions, Dealer’s access,
Experience at outlets & Relocation
services do not play an important
role.
2) Service Expectations
“BB-CSI: Managers (8.03) >> HW/Rtd
(5.33)”
 A unit increase in BB-CSI increases
intent to spend by 1.02 times
 Focus to make them key satisfiers
for the customer: Interactive
website, Variety of Packages,
Regular payment alerts, First-time
installation: “High Performance but
Low Importance”
3) Customer Service explains
21.018 % of the variance of data
“Customer Service & Usage Experience
are two most important areas for the
customers”
 Overall experience is highly
correlated with Download Speed,
Maintenance options at 0.42 & 0.41
respectively
 Weakest correlation is shown by
Experience of Change of service at
0.20
4) Broadband providers Effective in
Delivering Service Attributes of
High Importance
“Behavior of Installation staff,
Recharge flexibility, Plans & Offers, Wi-
Fi Connectivity, Activation of first time
services, Download speed & valued
pricing have been delivered efficiently
by the Service Providers”
 Focus areas: Trustworthiness,
Maintenance & Repair options.
5) 41% of the sample shows strong
faith in Broadband providers
“Overall analysis of customer behavior
also indicates that 41% of the sample
shows characteristics of being
vulnerable”
 91/221 customers champions
category of the satisfaction-
loyalty grid
 Champions have high service
experience
 Switchers (13%) obtained
pleasant service experience;
observed to be not loyal

Page29
6) Survival Analysis explains
momentum of churn & relevance
of customer categories
“Antagonists & Switchers formulate
focus segments for the provider”
 The model explains that the
framework is well contributed to by
the choice of customer segments
alpha value being <0.05
 The survival curve depicts that the
intent to churn builds up after a
period of 1 year & is within 1 year to
3 years of the service usage
 The hazard plot explains that
Antagonists is the churning
category of customers should be
prioritized in terms of retention
strategies.
7) Kano’s Grid defines relevance of
service attributes to be
triangulated upon
“Customer sentiment index will indeed
show a relevant change if strategies are
built to better the focus areas”
 Differentiation for service provider
can be obtained if the delight factors
(Advertisement & Promotions;
Value to the customers & First-time
installation services) are focussed
upon
 Download Speed, Continued
service in heavy rains, Recharge
Flexibility, Behaviour of Installation
staff are key drivers & provide apt
customer satisfaction. SPs should
fulfil such attributes & maintain
position.
8) Churn Model – Insightful
depiction of customer behaviour
“A unit increase in BB-CSI decreases
churn by 0.22 times”
 Speed issues, Billing & Recharge
issues Activation & Deactivation
issues , formulate major complaint
areas (approx.. 54% of the
sample)good
 Majority of customers i.e. approx.
51% churn due to better services &
offers by other service providers.
 Another positive trend depicts 78%
of sample not planning to change
due to trusted service experience.

Page30
6 RECOMMENDATIONS & DISCUSSIONS
6.1 CONCLUSIONS & DISCUSSIONS
Customer sentiment is poised to become a key differentiator & a source of competitive
advantage. Thus it is important for the Broadband providers to acknowledge the
difference between Quality of Service; Quality of Satisfaction & Quality of Experience;
Customer Sentiments.
The results conclude that today the service industry greatly relies on the customer
sentiment – Also the Key differentiator for the Broadband providers.
 Customer Awareness builds choice & brand image.
 Performance of the brand leads to better experience & amplifies satisfaction.
 Minimizes churn along with acquisition of new customers through referrals.
 Customer Experience plays a vital role in the Broadband Telecom Segment.
The Broadband-CSI when conducted on a full scale would help the broadband
providers demarcate the line between customer satisfaction and experience, & build
on strategic decisions, helpful to the business.
The Broadband-CSI will assist the service providers in the following ways:-
Observe customer behavior: Brand Loyalty patterns
What it takes to positively impact customer sentiments
Fine Tune Marketing Strategies
Identify Profitable Customer Segments
Table 7 (Concluding Statements)
Quality of Service
Drives
Service Providers Achieve:-
Competitive Advantage
Increased Customer Base
Increased Referrals
Long-term Alliance
Classify service attributes
Figure 17: Customer Sentiment Drivers

Page31
6.2 RECOMMENDATIONS
6.2.1 Advancement on the path
A customer centric approach would help the
broadband providers to measure sentiments &
evolve throughout the journey of service
industry.
Understanding the entire customer life-cycle;
to understanding the key touch points at every
stage of the cycle; prioritizing the segments in
accordance to the touch-points. Broadband-
CSI framework would help:-
 Evaluate current level of experience
 Evaluate the expectations of the customers
 Identify gap in the experiences
 Identify changes in people; processes & technology
 Prioritize & implement the changes
6.2.2 Recommendations
The recommendations are based on three major pillars of an organization i.e. People,
Process & Technology. Each recommendation poses respective business
connotations such as Word of Mouth, Trustworthiness, Loyalty, Costs etc.
Prioritize the
touch-points
Evaluate
Experiences
Identify the
touch-
points
Assess the
impact of
improved
customer
experience
Understand
the customer
behavior
Figure 18: Improving Broadband Customer Sentiment
New offerings & opportunities
can increase sales in broadband
Focus on High importance Low
performance areas
Integrate Voice of customer to
capture the stated & unstated
needs
Technology changes in customer
care services
Provide value added & discounted
packages
Innovative less budget
Advertising &
Promotion Campaigns
Regular complaint data
analysis; Effective handling
of the grievances
Training of Customer
Care & Field Personnel
Ala’carte packages should
be delivered
Effective marketing strategies
to increase spending intent
Provide customized packages
suited to customer needs
Increase LTV with long term
association
Provide ease of access &
knowledge
Consumers should be educated
as to how Broadband
completes internet needs

Pagea
ANNEXURES/APPENDIX
Reliability & KMO statistics
Importance Scale
Reliability Statistics
Cronbach's Alpha
N of
Items
.967 25
Experience Scale
Reliability Statistics
Cronbach's Alpha
N of
Items
.974 25
Factor Analysis outputs
KMO and Bartlett's Test
Kaiser-Meyer-Olkin Measure of
Sampling Adequacy.
.935
Bartlett's Test of Sphericity Approx.
Chi-
Square
3234.958
df 300
Sig. 0.000
Communalities
Initial Extraction
q2_1b 1.000 .803
q2_2b 1.000 .840
q2_3b 1.000 .721
q2_4b 1.000 .655
q2_5b 1.000 .756
q2_6b 1.000 .811
q2_7b 1.000 .679
q2_8b 1.000 .737
q2_9b 1.000 .813
q2_10b 1.000 .786
q2_11b 1.000 .742
q2_12b 1.000 .700
q2_13b 1.000 .747
q2_14b 1.000 .800
q2_15b 1.000 .785
q2_16b 1.000 .802
q2_17b 1.000 .765
q2_18b 1.000 .716
q2_19b 1.000 .780
q2_20b 1.000 .843
q2_21b 1.000 .794
q2_22b 1.000 .660
q2_23b 1.000 .809
q2_24b 1.000 .756
q2_25b 1.000 .764
Extraction Method: Principal
Component Analysis.
Rotated Component Matrixa
Component
1 2 3 4 5 6
q2_1b .799
q2_2b .828
q2_3b .663
q2_4b .492 .530
q2_5b .536
q2_6b .463 .550
q2_7b .585
q2_8b .431 .611
q2_9b .439 .691
q2_10b .767
q2_11b .744
q2_12b .542 .431
q2_13b .506 .630
q2_14b .759
q2_15b .595 .495
q2_16b .784
q2_17b .676
q2_18b .688
q2_19b .403 .598
q2_20b .802
q2_21b .697
q2_22b .481 .440
q2_23b .764
q2_24b .725
q2_25b .731

Pageb
Factors obtained on the basis of responses
Factor 1
Customer Helpline easy Acccess
Queries solved efficiently & quickly
Maintenance & Repair options
Helpline staff are polite & courteous
Experience at Outlets
Interactive website
Dealers are widely spread
Factor 2
Wifi Connectivity
Continued Service in heavy rains
Download Speed
Experience of change in service
Factor 3
I feel valued customer
Variety of Packages
Trustworthy operator
Factor 4
Plans & offers
Pricing is value
Total
% of
Variance
Cumulativ
e % Total
% of
Variance
Cumulativ
e % Total
% of
Variance
Cumulativ
e %
1 15.502 62.008 62.008 15.502 62.008 62.008 5.255 21.018 21.018
2 1.408 5.631 67.638 1.408 5.631 67.638 3.447 13.787 34.805
3 1.064 4.257 71.896 1.064 4.257 71.896 2.943 11.774 46.579
4 .892 3.567 75.463 .892 3.567 75.463 2.911 11.643 58.223
5 .728 2.911 78.373 .728 2.911 78.373 2.875 11.502 69.725
6 .680 2.721 81.094 .680 2.721 81.094 2.842 11.370 81.094
7 .560 2.241 83.335
8 .487 1.950 85.285
9 .436 1.743 87.028
10 .415 1.660 88.688
11 .331 1.323 90.011
12 .314 1.254 91.265
13 .297 1.187 92.452
14 .257 1.028 93.480
15 .246 .985 94.465
16 .227 .910 95.375
17 .188 .754 96.128
18 .183 .733 96.862
19 .163 .653 97.514
20 .150 .599 98.113
21 .128 .513 98.627
22 .117 .468 99.095
23 .088 .353 99.448
24 .070 .282 99.730
25 .068 .270 100.000
Total Variance Explained
Compone
nt
Initial Eigenvalues Extraction Sums of Squared Rotation Sums of Squared
Extraction Method: Principal Component Analysis.

Pagec
Accurate (Fair) Charge deduction
Activation of first time services
Factor 5
Promotions
Advertisements
Experience in Relocation of services
Factor 6
Regular payment alerts
Recharge Flexibility
Behavior of installation staff
Binary Logistic Regression Overall Experience
B S.E. Wald df Sig. Exp(B)
ACEI_Scor
e
.477 .117 16.693 1 .000 1.611
Constant -1.173 .697 2.827 1 .093 .310
ACEI_Scor
e
.427 .108 15.769 1 .000 1.533
Constant -1.589 .684 5.402 1 .020 .204
ACEI_Scor
e
-.249 .089 7.739 1 .005 .780
Constant .349 .584 .357 1 .550 1.418
ACEI_Scor
e
-.202 .080 6.350 1 .012 .817
Constant .704 .541 1.691 1 .193 2.022
ACEI_Scor
e
.023 .078 .088 1 .767 1.023
Constant .452 .538 .707 1 .401 1.571
Step 1a
a. Variable(s) entered on step 1: ACEI_Score.
Less Complaints Raised
Step 1a
Spend More for BetterServices
Step 1
a
Customer Churn
Step 1a
Chances of Recommendation
Step 1
a
Purchase More Services

Paged
REFERENCES:-
[1] Chandra Varun, (2010), "Innovation Practices & There Measurements in Telecom
Industry"
[2] Fiedler Markus, Möller Sebastian, and Reichl Peter, (2012), "Quality of
Experience: From User Perception to Instrumental Metrics"
[3] Leone P. Robert, Petersen Andrew J. and Kumar V., (2007), "How Valuable is
Word of Mouth"
[4] Lieberman Michael, (2008), "Adding value to CSM: the Kano Model"
[5] Lu Junxiang, Paper, “Modeling Customer Lifetime Value Using Survival Analysis
− An Application in the Telecommunications Industry”
[6] Lu Junxiang, Paper, “Predicting Customer Churn in the Telecommunications
Industry –– An Application of Survival Analysis Modeling”
[7] Mamatkhodjaev Timur, (2007), "Technologies & Services"
[8] McIvor Ronan, (2008), "What is the right outsourcing strategy for your process?"
[9] Muldowney David, Foley Christopher, Davy Steven & Adhikari Anwesh, (2011),
"Increasing Mobile Network Operators Profitability - The role of Self Organised
Networks"
[10] Odujobi Oladayo, (2010), "Service Quality Relevance in Nigeria: Evidence from
Zain Mobile"
[11] Patel Shail and Schlijper Antoine, "Models of Consumer Behaviour"
[12] Peter C. Verhoef, Katherine N. Lemon, A. Parasuraman, Anne Roggeveen,
Michael Tsiros, Leonard A. Schlesinger (2009) , "Customer Experience Creation:
Determinants, Dynamics and Management Strategies"
[13] Pfeifer E. Phillip, Haskins E. Mark, Conroy M. Robert Conroy, (2004),
"Customer Lifetime Value, Customer Profitability, and the Treatment of Acquisition
Spending"
[14] Pezeshki Vahid, (2009), "Three Dimensional Modelling of Customer Satisfaction,
Retention and Loyalty for Measuring Quality of Service"
[15] Philpott Sara, IBM (2010), "Global Telco Business Analytics & Optimization
Centre of Excellence"
[16] Pricewaterhouse Coopers, (2011), "Curing customer churn"

Pagee
[17] Produced by logme.com, (2012) "How can customer experience make a
Difference?"
[18] Raman Sundara, Teradata, (2011), "Analytics in Next-Generation Telecom
Services"
[19] Reichheld F. Fredrick, (2003), "The One Number You Need To Grow"
[20] Reinartz Werner and Kumar V., (2002), "The Mismanagement of Customer
Loyalty"
[21]Sellers Ron, (1998), "Outsource It Or Keep It In-House?"
[22]Smith Tyler, Smith Besa, Paper, “Survival Analysis And The Application Of Cox's
Proportional Hazards”
[23]Teck H. Ho, Noah Lim, Colin F. Camerer, (2005), "Modeling the Psychology of
Consumer and Firm Behavior with Behavioral Economics"
[24]Toman Nicolas, Freeman Karen, and Dixon Matthew, (2010), "Stop Trying to
Delight Your Customers"
[25]Venkatesan Rajkumar & Kumar V., (2004), "A Customer Lifetime Value
Framework for Customer Selection and Resource Allocation Strategy
[26]White Paper by Telecordia, (2009), " Trouble-to-Resolution: Fewer and Faster"
[27]White-Paper, TM-Forum, (2012), "Customer Experience Management -
Introduction & Fundamentals"
[28]White-Paper, TM-Forum, (2013), "Customer Experience Management Index"
[29]Willcocks P. Leslie and Feeny David, (2006), "IT Outsourcing and Core Is
Capabilities: Challenges and Lessons at Dupont"
[30]Xu Qianli, Jiao J. Roger, Yang Xi and Helander Martin, (2008), "An analytical
Kano model for customer need analysis"

Pagef
WEBSITES:-
1) http://pic.dhe.ibm.com/infocenter/spssstat/v20r0m0/index.jsp?topic=%2Fcom.ibm.spss.sta
tistics.help%2Frfm_intro.xml.htm
2) http://www.investopedia.com/terms/r/rfm-recency-frequency-monetary-value.asp
3) http://searchdatamanagement.techtarget.com/definition/RFM-analysis
4) http://hbr.org/2011/06/why-customer-referrals-can-drive-stunning-profits/ar/1
5) http://people.ucalgary.ca/~design/engg251/First%20Year%20Files/kano.pdf
6) http://www.sciencedirect.com/science/article/pii/S0925527308001084
7) https://www.custora.com/tour/feature_predictive_customer_lifetime_value_clv_retail
8) http://www.localytics.com/blog/2013/importance-of-customer-lifetime-value/

Research project on customer sentiment index

More Related Content

What's hot (20)

Viewers also liked (7)

Similar to Research project on customer sentiment index (20)

More from Aditya Basu (6)

Recently uploaded (20)

Research project on customer sentiment index