Marketing Analysis

This marketing analysis focuses on developing a prediction model to predict customer churn for Tesco PLC using the Tesco Clubcard data. The research methodology involves collecting data from 30,000 customers over a period of 1 year and developing a decision tree model. The results section discusses the variables that lead to churning and non-churning customers. The implications of the analysis in retaining customers and reducing expenses are discussed in the conclusion.

Running Head: MARKETING ANALYSIS
Marketing Analysis
Name of the Student
Name of the University
Student ID

1MARKETING ANALYSIS
1.0 Introduction and Problem Definition
A British multinational supermarket chain who has its headquarter in Welwyn Garden
City, Hertfordshire, England, United Kingdom is the Tesco PLC. In terms of profit, Tesco PLC is
the third largest retailer and in terms of revenue, Tesco PLC is the second largest retailer. It is a
multipurpose company with 12 stores spread all across the globe.
A new customer loyalty scheme was launched by Tesco known as the Tesco Clubcard.
The scheme had two levels – Gold and Silver. With the introduction of this scheme, the aim of
Tesco to become the largest supermarket chain in UK has become successful.
Thus, the main interest in this research is to develop a prediction model which will be
helpful in predicting the churn of the customers.
2.0 Literature Review
Related articles and previous researches that will describe the situation in
consideration to this research needs to be discussed in this section. Studies that can be related
in predicting the customer churn or customer satisfaction in any company can be discussed
here. The factors that are responsible for employee retentions according to previous studies
needs to be discussed.
3.0 Research Methodology
To perform this task, data has been collected from the Tesco Clubcard. 30,000
customers were selected randomly from the Tesco Clubcards. Data was collected over a
period of 1 year from 1st January 2015 to 31st December, 2015. Information is available on 18
different variables. The prediction model has to be developed on the basis of these variables.
The churn of the customers in buying from Tesco stores is to be predicted. Here,
churn is a binary variable having two values – churner and non-churner. The prediction

2MARKETING ANALYSIS
model to be developed in this assignment is a decision tree. With the help of a decision tree,
the dependent variable can be predicted. The outcomes with the respective probabilities and
their impact on the next variable can be established clearly with the help of tree like diagram
in this method.
4.0 Results
After developing the tree, the results section will be written, in which discussions
based on the outcome of the prediction model will be considered. Which variables lead to a
churning customer and which conditions lead to a non-churning customer will be discussed in
this section.
This model developed with the help of a decision tree will be a much more precise
model than just a random guessing. In order to compare, the measures of precisions for both
the prediction techniques can be compared and the model with a better precision will be
considered as a better prediction model.
5.0 Conclusion
The implications of the results obtained from the analysis will be discussed here. The
contribution of the implications derived from the analysis in retaining the customers of Tesco
and hence to reduce the expenses in the market can be discussed in this section.