1

CMI236

1. Introduction customer analytics

Preamble
The emphasis in marketing is the identification and satisfaction of customer
needs.
In order to determine customer needs and to implement marketing strategies and
programs aimed at satisfying those needs, marketing managers need
information.
They need information about customers, competitors, and other marketing
environmental forces.
As consumers have become more affluent & sophisticated, marketing managers
need better information on how they will respond to products and other
marketing offerings.
As competition has become more intense, managers need information on the
effectiveness of their marketing tools, and as the environment changes more
rapidly, marketing managers need more timely information
The role of customer analytics is to assess the information needs and provide
management with relevant, accurate, reliable, valid, current and actionable
information
So customer data analytics entail a thorough research about customers, which
involves undertaking a systematic process to find out things about business and
management (Saunders et al.,1997)
‘Systematic’ suggests that research is based on logical relationship and not just
beliefs (Ghauri et al., 1995).
As part of this your research will involve an explanation of the methods used to
collect data, argue why results are the way they are, argue why the results
obtained are meaningful and explain any limitation associated with them.
Finding out’ suggests a multiplicity of possible purposes of your research eg
describing, explaining, criticising, analysing, understanding, etc
Customer Analytics defined
2

Customer analytics can also be called customer data analysis

It is the process of collecting, analysing customer data to gain insights on
consumer behaviour
It can also be defined as the process of collecting and analysing customer data to
understand customer needs, price sensitivity, doubts in choosing products and
services and develop targeted marketing and sales activities
Customer analytics help business to make better strategies, build better products
and provide better services to their customer
So basically, Customer Analytics has four main elements, thus data collection,
data sorting, data storage and data analysis.
Key features for customer data
1. Customer data collection
2. Data management
3. Segmentation, Targeting and Positioning
4. CRM
Types of Customer Data
1. Transactional Data
This is data from product or service purchase, returns or reservations
2. Data about product usage
This is understanding product or service utilisation patterns
3. Web behaviour data
This is the data from analysis of pages opened by by customers, how they view,
scrolling down on company websites
4. Data from customers
Analysis of customers’ online reviews or social media posts about a company’s
products or services

There are 4 types of Customer Analytics

1. Descriptive C.A (what happened?)
Discovering what has happened or what is happening by analysing historical and
real time customer related data e,g revealing a drop in sales over the last month
3

2. Diagnostic C.A (why did it happen?)

Finding root causes of business problems by analysing both internal and external
customer related data
3. Predictive C.A (what will happen?)
Making prediction and forecasts using data mining and machine learning
techniques and real time customer data e,g estimation of how much revenue
could be gained if customers are offered a discount for their next purchase
4. Prescriptive C.A (what should be done?)
Suggesting the best possible course of action based on the predictive analytics’
estimation of future events e.g offering a 5% coupon to a particular segment to
get maximum revenue increase from it

2. Why business need customer analytics

(1) Understand your customers and their preferences (4 Ps)

 Profile your customers (location, age, gender, income level, etc.)
 To guide interactions with customers
 Get customer complaints
 Customer satisfaction and retention
 Create more effective marketing campaigns
 Find the best business location
(2) Identify opportunities to grow and increase profits
 Recognize changes in demand
 Offer new products or services for the new demand
 Find new markets within and outside of Zimbabwe

(3) Recognize and plan for industry and economic shifts

 Shift inventory, price and staff levels as needed
(4) Monitor the competition in your market
 Identify competitors
 Get information on how your competitors operate
 Learn how customers compare you with your competitors
4

(5) Mitigate risk in your business decisions

Use information, not just intuition, to drive your business decisions

(6) To find gaps in the market

So all this will help in the STP process, where marketers will know how to
segment, how to target and how to position their products.
b) Customer Lifetime Value
c) CRM
d) Retention and Lifetime value
In customer data collection, marketers undertake what is known as marketing
research.
Marketing Research Defined
A systematic and objective identification, collection, analysis, dissemination, and
use of information for the purpose of assisting management in decision making
related to the identification and solution of problems and opportunities in
marketing (AMA, 2009)
Marketing research is the function that links the consumer, customer and public
to the marketer through information-information used to identify and define
marketing opportunities and problems; generate, refine, and evaluate marketing
actions; monitor marketing performance; and improve understanding of the
marketing process.
Marketing research is the systematic gathering, recording, and analysis of
quantitative and qualitative data about issues relating to marketing products and
services.
The goal is to identify and assess how changing elements of the marketing mix
impacts customer behaviour.
The definition of marketing research states that organisations undertake research
for two purposes :(1) to identify and to (2) solve marketing problems.
Subsequently, this distinction can be used as a basis for classifying marketing
research into Problem Identification Research and Problem Solving Research
Problem identification research
5

Research that is undertaken to help identify problems that are not necessarily
apparent on the surface and yet exist or are likely to arise in the future.
Provides information about the marketing environment and helps diagnose a
marketing problem.
Increasing market potential vs declining market share.
The recognition of economic, social, or cultural trends such as changes in
consumer behaviour, may point to underlying problems and opportunities.
This include the following types of research:
1. Market Potential Research
2. Market Share Research
3. Image Research
4. Market characteristics Research
5. Sales Analysis Research
6. Forecasting Research
7. Business Trends Research

Problem solving research

Research undertaken to help solve specific marketing problems
Problem Identification and Problem solving research goes hand in hand and they
also follow a common research process
This includes the following types of research
1. Segmentation Research
2. Product Research
3. Pricing Research
4. Promotion Research
5. Distribution Research

In customer data analytics now, you follow the marketing research process

THE MARKETING RESEARCH PROCESS IN ANALYTICS

A set of steps that defines the tasks to be accomplished in conducting a
marketing research study.
6

These include problem definition, development of an approach to the problem,

research design formulation, fieldwork, data preparation and analysis, and report
preparation and presentation
The process follows the following steps:
1. Marketing Problem Definition
2. Development of an approach to the definition
3. Research Design formulation
4. Fieldwork or Data Collection
5. Data Preparation and Analysis
6. Report preparation and presentation

This involves stating the general problem and identifying the specific
components of the research problem.

-only when the marketing research problem has been CLEARLY defined can
research be designed and conducted properly.

- All the effort, time, and money spent after the definition of the problem will be
wasted if the problem is misunderstood or ill-defined.
3. Colleting customer analytics data
A framework or blue print for conducting the marketing research is called the
methodology
Details the procedures necessary for obtaining the required information & its
purpose is to design a study that will test the hypothesis of interest, determine
possible answers to the research questions, and provide the information needed
for decision making
A research design constitutes the blueprint for the collection, measurement, and
analysis of data.
Research design involves;
1. Definition of the information needed
2. Secondary data analysis
3. Quantitative /Qualitative Research
4. Methods of collecting quant. Data
7

5. Measurement and scaling procedures

6. Questionnaire design

7. Sampling process

8. Plan of data analysis

The purpose of research design is to structure the research so that it delivers the
evidence necessary to answer the research problem as accurately, clearly and
unequivocally as possible.

Types of customer data

Data can be classified into 2 categories, primary and secondary data

Secondary Data

Secondary data refers to data collected by someone other than the primary user.

Examples of secondary data include surveys, experiments, observations,

Government publications, websites, books, journal articles, internal records etc.

Primary Data

Primary data refers to data that has been generated by the researcher
himself/herself through surveys, interviews, experiments, questionnaires,
observations specifically designed for understanding and solving the research
problem.
1. Quantitative Data collection metrics
Groups to do… (Questionnaires, types and how to design them)To talk of the
advantages and disadvantages of using a questionnaire

2. Qualitative Data collection Metrics

In groups students discuss observations, focus groups, interviews and outline
advantages and disadvantages.
Target Population
8

A population is the aggregate of all the elements that share some common set of
characteristics and that comprise the universe for the purpose of the marketing
research problem.
The population parameters are typically numbers, such as the proportion of
consumers who are loyal to a particular brand of toothpaste.
Sample
A small part or quantity intended to show what the whole is like.
Sample size
Sample size determination is the act of choosing the number of observations or
replicates to include in a statistical sample.
The sample size is an important feature of any empirical study in which the goal
is to make inferences about a population from a sample.

3. Sampling Techniques
The objective of most marketing research projects is to obtain information about
the characteristics or parameters of a population.
Information about population parameters may be obtained by taking a census or
a sample.
A census involves a complete enumeration of the elements of a population.
The population parameters can be calculated directly in a straightforward way
after the census is enumerated.
A sample, on the other hand as stated earlier is, a subgroup of the population
selected for participation in the study.
Sample characteristics, called statistics, are then used to make inferences about
the population parameters.
The inferences that link sample characteristics and population parameters are
estimation procedures and tests of hypotheses.
Classification of sampling techniques
Sampling techniques can be divided into 2 categories:
9

1. Probability sampling - a sampling procedure in which each element of the

population has a fixed probabilistic chance of being selected for the
sample.
In probability sampling every element in the population has a known non-zero
probability of selection e.g simple random sample is the best known probability
sample, in which each member of the population has an equal probability of
being selected.
Probability sampling techniques
A. Simple Random Sampling;
 A probability sampling technique in which each element has a known
and equal probability of selection.
 Every element is selected independently of every other element, and
the sample is drawn by a random procedure from a sampling frame.
 A sampling procedure that assures each element in the population
an equal chance of being included in the sample.
 E.g. Include:
 drawing names from a hat/box
 Selecting the winning raffle from a large drum
 Using random numbers
If any of the processes are done thoroughly each person should have an equal
chance of being selected.
The sampling process is simple because it requires only one stage of sample
selection.
Drawing names or numbers out of a fish bowl, using a spinner, rolling dice or
turning a roulette wheel may be used to draw a sample from a small population.
When population consist of large numbers of elements, however, tables of
random numbers or computer- generated random numbers are utilized for sample
selection.

B. Systematic Sampling
10

A probability sampling technique in which the sample is chosen by selecting a

random starting point and then picking every ith element in succession from the
sampling frame.
The sampling interval, i, is determined by dividing the population size N by the
sample size n and rounding to the nearest whole number.
For example, there are 100,000 elements in the population and a sample of 1000 is
desired. In this case, the sampling interval, I, is 100.
A random number between 1 and 100 is selected. If, for example, this number is
23, the sample consists of elements 23, 123, 223, 323, 423, 523, and so on
An initial starting point is selected by a random and then the factor of selection is
determined by using the following formula:

K= N/n
Although this procedure is not actually a random selection procedure, it yields
random results if the arrangement of the items in the list is random in character.
A probability sampling technique that uses a two-step process to partition the
population into subsequent sub-populations, or strata.
C.STRATIFIED SAMPLING
Is a probability sampling procedure in which sub-samples are drawn from
samples within different strata that are more or less equal on some
characteristics?
The strata should be mutually exclusive and collectively exhaustive in that every
population element should be assigned to one and only one stratum and no
population elements should be omitted.
Next, elements are selected from each stratum by a random procedure, usually
SRS.
The variables used to partition the population into strata are referred to as
stratification variables.
The elements within a stratum should be as homogeneous as possible, but the
elements in different strata should be as heterogeneous as possible.
The stratification variables should also be closely related to the characteristic of
interest.
11

Variables commonly used for stratification include demographic characteristics,

type of customer (e.g. credit card versus non-credit card), size of firm, or type of
industry.
A major objective of stratified sampling is to increase precision without
increasing cost.
E.g. suppose urban and rural groups differ widely on attitudes towards energy
conservation, yet members in each group hold very similar attitudes.
Random sampling error is reduced because the groups are internally
homogeneous but comparatively different.
Another reason for stratified sample is that the sample will accurately reflect the
population on the basis of criterion or criteria used for stratification.
This is a concern because occasionally a simple random sample a
disproportionate number of one group or another and the representativeness of
the sample could be improved.

D.CLUSTER SAMPLING
In cluster sampling, the target population is first divided into mutually exclusive
and collectively exhaustive sub-populations.
These sub-populations or clusters are assumed to contain the diversity of
respondents held in the target population.
A random sample of clusters is selected, based on a probability sampling
technique such as SRS.
For each selected cluster, either all the elements are included in the sample or a
sample of elements is drawn probabilistically.
If all the elements in each selected cluster are included in the sample, the
procedure is called one-stage cluster sampling.
If a sample of elements is drawn probabilistically from each selected cluster, the
procedure is two-stage cluster sampling.
A common form of cluster sampling is area sampling, in which the clusters
consist of geographic areas, such as counties, housing districts or residential
blocks.
12

2. Non-probability sampling
-Sampling techniques that do not use chance selection procedures but rather rely
on the personal judgement of the researcher.
In a non-probability sampling the probability of any particular member of the
population being chosen is unknown.
The selection of sampling units is quite arbitrary, as researchers rely heavily on
personal judgement
A. CONVINIENCE SAMPLING
A non-probability sampling technique that attempts to obtain a sample of
convenient elements.
The selection of sampling units is left primarily to the interviewer.
Respondents are often selected because they happen to be in the right place at
the right time.
For example, (1) use of students, church groups and members of social
organisations, (2) street interviews without qualifying the respondents, (3)some
forms of email and Internet survey
Convenience sampling is the least expensive and least time-consuming of all
sampling techniques.
However, the disadvantage is that it has many potential sources of selection bias,
including respondent self-selection.
Convenience samples are also not representative of any definable population.
Hence, it is not theoretically meaningful to generalise to any population from a
convenience sample.
Convenience samples can be used for exploratory research, pre-testing
questionnaires, or pilot studies.
B. JUDGEMENTAL SAMPLING
A form of convenience sampling in which the population elements are purposely
selected based on the judgement of the researcher.
13

The researcher, exercising judgement or expertise, chooses the elements to be

included in the sample because he or she believes that they are representative of
the population of interest or are otherwise appropriate.
Common examples of judgemental sampling include: (1) test markets selected to
determine the potential of a new product, (2) supermarkets selected to test a new
merchandising display system.
Judgemental sampling is inexpensive, convenient and quick, yet it does not allow
direct generalisations to a specific population, usually because the population is
not defined explicitly.
Judgemental sampling is subjective and its value depends entirely on the
researcher’s judgement, expertise and creativity &
It can be useful if broad population inferences are not required

C. QUOTA SAMPLING
A non-probability sampling technique that is a two-stage restricted judgemental
sampling.
The first stage consists of developing control categories or quotas of population
elements such as gender, ethnicity, age groups, socio-economic groups, and
region of residence, and in combinations of these categories.
To develop these quotas, the researcher lists relevant control characteristics and
determines the distribution of these characteristics in the target population, such
as Males 49% & Females 51%
In the second stage, sample elements are selected based on convenience or
judgement.
Once the quotas have been assigned, there is considerable freedom in selecting
the elements to be included in the sample.
The only requirement is that the elements selected fit the control characteristics

D.SNOWBALL SAMPLING
14

A non-probability sampling technique in which an initial group of respondents is

selected, sometimes on a random basis, but more typically targeted at a few
individuals who are known to possess the desired characteristics of the target
population.
Subsequent respondents are selected based on the referrals or information
provided by the initial respondents.
Even though probability sampling can be used to select the initial respondents,
the final sample is a non-probability sample.
The referrals will have demographic and psychographic characteristics more
similar to the persons referring them than would occur by chance
Used to estimate characteristics that are rare in the wider population.
Examples include; locating members of a scattered minority ethnic group,
widowed males under 35 etc

4. Measuring validity and reliability

The credibility of research findings is neatly expressed by Raimond (1993:55)
when he subjects findings to the:
 How do I know?
 Will the evidence and my conclusions stand up to the closest scrutiny?
 How do I reduce the biasness of my results?
 Reducing the possibility of getting the answer wrong means that
attention has to be paid to two particular emphases on research:
reliability and validity
Reliability
Reliability can be assessed by posing the following two question (Easterby-Smith
et al., 1991:41):
Will the measure yield the same results on different occasions?
Will similar observations be made by different researchers on different
occasions?
How to ensure reliability of customer data collected
15

1. Triangulation- the researcher uses a combination of methods, for example, a

questionnaire to quickly collect a great deal of information from a lot of people,
and then interviews to get more in-depth information from certain respondents to
the questionnaires.

Perhaps case studies could then be used for more in-depth analysis of unique
and notable cases, e.g., those who benefited or not from the program, those who
quit the program, etc
Triangulation involve the use of different approaches, methods and techniques in
the same study.”
Triangulation can overcome the potential bias and sterling of a single method
approach.
Denzin(1970) defines triangulation as the combination of methodologies in the
study of the same phenomenon.
He argues that the use of different methods by a number of researchers studying
the same phenomenon should, if their conclusion are the same, lead to greater
validity and reliability than a single methodological approach.
Smith, Thorpe and Lowe (1991) identify four types of triangulation:
1. Data Triangulation- where data is collected at different times or from different
sources in the study of a situation.
2. Investigation Triangulation- where different researchers independently collect
data on the same situation and compare the results.
3. Methodological triangulation- where both quantitative and qualitative methods
of data collection are used.
4. Triangulation for theories- where a theory is taken from one discipline and used
to explain a situation in another discipline
The approaches and strategies do not exist in isolation and therefore can be
mixed and matched.
It is common for a study to combine both quantitative and qualitative methods
and to use secondary and primary data.
For example, you can use a survey method for a broad area to get general
knowledge and use case study to get in-depth understanding or information.
16

Threats to reliability
Robson (1993) asserts that there may be four threats to reliability.
1. Subject error- a questionnaire completed at different times of the week may
generate different results.
2. Subject bias- interviewees may have been saying what they thought their
bosses wanted them to say eg authoritarian managed organisation.
3. Observer error-researchers may use different approaches to elicit answers
from respondents.
4Observer bias- deals with the interpretation of responses
Validity
Is concerned with whether the findings are really about what they appear to be
about.
Robson (1993) has also charted the threats to validity which provides a useful
way of thinking about validity.
Types of validity
How to ensure data validity
Threats to validity
1. History-information you get after an event happening may be misleading.
2. Testing-if respondents think that the results of the outcome may disturb them
in some way this is likely to affect the outcome
3. Instrumentation- what instrument has been used to collect the data.
4. Mortality-this refers to participants dropping out of studies.
5. Maturation-other events happening during the year have an effect on
participants.
6 Ambiguity about casual direction
7. Generalisability- sometimes referred to as external validity. A concern you may
have in the design of your research is the extent to which your results are
generalisable, ie. Your findings may be equally applicable other research
settings.

Ethical considerations in customer data collection

17

Asenahabi (2019) says that ethical issues in research are a collection of

guidelines that influence the methodology and research design
Research ethics encourage honesty, integrity, mutual respect, trust,
confidentiality, responsibility and adherence to purpose of generating good
rather than damage
In data collection, marketers should abide to the POPIA Act, The Protection of
Personal Information Act of 2018 that protects the rights of the respondents
No individuals should be forced or coerced or bribed to be a respondent but they
should do it willingly

4. Data analysis
The five step process:
1. Prepare and organise your data.
2. Review and explore the data.
3. Create the initial codes.
4. Review these codes and revise or combine into themes
5. Present themes in a cohesive manner.
Significance to marketing strategies development
Conduct a field research to find out who buys the product? Who uses it? Who
are the prospective buyers and users? The survey will reveal the characteristics
that differentiate the market segment making up the product’s market
potential. Survey provides customer data on factors such as purchase
frequency, searching time, unit of purchase and seasonal buying habits.
When assembled and analyzed, this data helps in establishing market and sales
potential

You then look for best way to achieve your objective, one can use the Ansoff
matrix BCG; Cost strategy, Differentiation strategy etc. this step in the process is
complicated by the fact that there are often many alternative ways in which each
objective can be achieved. Although several strategies may be evaluated, only
18

one strategy can be applied. This gives rise to the formula; one strategy per
objective.
You then develop activities or tactics
These are detailed plans of what needs to be done. When, whom, where, what
communication tools, how much to spend, marketing mix etc

Allocate necessary resources

Once tactics are developed, resources must be allocated to carry out the plans.
5 Ms (machinery, minutes, material, manpower, money)
Implementing the plan
The procedure so far would have resulted in the preparation of detailed document
setting out what is to be done, when it will be done, who is responsible and
estimated cost and revenues as well as agreed time frames for the various
activities in the plan. It requires close monitoring, some companies use full time
project coordinators to see who does what and at what time. For example, if
you are using different communication tools, is the message being delivered
single and consistent. It should seek to achieve a distinctive voice of one clear
message. Details of the marketing plan should be communicated to everyone
involved. Many companies have elaborate marketing plans that are not
implemented because key people have not been informed or have not agreed to
the proposed plan.
Controlling the plan
It is necessary that during planning you put down control measures in case
of deviations. Details of major objectives and key parameters in the measurement
of the degree of success in achieving the objective should be included, enabling
corrections and modifications to be made as the plan unfolds. The control part of
marketing plan should specify what should be measured, how it should be
measured and what data will be required for measurement. It may also include
details of what action is to be taken in the light of deviations from the plan. This
contingency planning is a key feature of any planning process, recognizing as it
does that plans need to be flexible in order to accommodate possible unforeseen
19

and unpredictable changes in the market. Performance measures usually used as

sales volume, new account, selling costs, sales force turnover, market share and
profit margins.
20

LIST OF REFERENCES
Abeyasekera, S. 2005. Multivariate methods for index construction. In:
Department of Economic and Social Affairs Statistics Division. Household sample
surveys in developing and transition countries. New York: United Nations.
African Response. 2006. FinScope small business survey report Gauteng 2006.
[Online] Available from: http://www.finscope.co.za/sme.html.
Alexander, C.E., Wilson, C.A. & Foley, D.H. 2005. Agricultural input market
segments: who is buying what? Journal of Agribusiness, 23(2):113-132.
Babbie, E. 2011. The basics of social research. 5th ed. Belmont, USA: Wadsworth.
Bailey, C., Baines, P.R., Wilson, H. & Clark, M. 2009. Segmentation and customer
insight in contemporary services marketing practice: why grouping customers is
no longer enough, Journal of Marketing Management, 25(3):227- 252.
Baker, M.J. 2002. Sampling. The Marketing Review, 3(1):103-120. [Online]
Available from: EbscoHost: Business Source Premier: http://0-
Borgatti, S.P. 2005. Thinking theoretically. [Online] Available from:
http://www.analytictech.com/mb870/handouts/theorizing.
Burton, D. 2002. Towards a critical multicultural marketing theory. Marketing
Theory, 2(2):207-236. [Online] Available from: Sage:
Canever, M.D., Van Trijp, H. & Van der Lans, I. 2007. Benefit-feature segmentation:
A tool for the design of supply-chain strategy. Marketing Intelligence & Planning,
25(5):511-533.
Cant, M.C., Strydom, J.W., Jooste, C.J. & Du Plessis, P.J. 2006. Marketing
Management. Cape Town: Juta & Co.
Christensen, C.M. & Raynor, M.E. 2003. Why hard-nosed executives should care
about management theory, Harvard Business Review, 81(9):67-74.
Clarke, A.H. & Freytag, P.V. 2008. An intra- and inter-organisational perspective
on industrial segmentation: A segmentation classification framework, European
Journal of Marketing,
Clark, L.A. & Watson, D. 1995. Constructing validity: basic issues in objective
scale development. Psychological Assessment, 7(3):303-319.
Tustin, D.H., Ligthelm, A.A., Martins, J.H. & Van Wyk, H. de J. 2005. Marketing
research in practice. SA: UNISA Press.