Case Study: Customer Segmentation for
Strategic Decision Making
1. Business Context
A fast-growing retail company has recently expanded its presence across both online and
offline platforms. The company serves a diverse customer base with varying purchasing
behaviors, income levels, and product preferences.
Despite having a large volume of customer data, the company currently follows a generic
marketing strategy, offering similar promotions and recommendations to all customers. This
has resulted in:
• Low conversion rates
• Inefficient marketing spend
• Lack of customer personalization
To address this, the management has decided to adopt a data-driven segmentation
approach to better understand its customers and tailor strategies accordingly.
2. Data Provided
You have been provided with a dataset(provide at the end of the exercise) containing
customer attributes such as:
• Age
• Monthly Income
• Spending Score
• Purchase Frequency
• Online Activity (Visits per Month)
• Preferred Product Category
• Gender
3. Your Role
You are part of the Business Analytics team. Your task is to analyze the dataset and
identify distinct customer segments without any predefined labels.
4. Problem Statement
Using the given dataset, answer the following:
Q1. Data Understanding
• Analyze the dataset and describe key patterns or trends you observe.
• Are there any relationships between income and spending behavior?
• Do younger customers behave differently from older customers?
Q2. Customer Segmentation
• Create 3–5 meaningful customer segments based on similarities in behavior and
attributes.
• Clearly describe each segment.
• Provide a suitable name for each segment (e.g., “High-Value Young Spenders”, “Low
Engagement Customers”).
Q3. Business Interpretation
• For each segment, explain:
o Key characteristics
o Customer behavior
o Potential value to the business
Q4. Strategic Recommendations
• Suggest targeted marketing or business strategies for each segment.
• Examples:
o Discounts
o Loyalty programs
o Personalized recommendations
o Premium offerings
Q5. Reflection
• Did different features lead you to different segmentation results?
• Which attributes were most important in your analysis and why?
• What challenges did you face while grouping customers without predefined labels?
Important Instructions
• Do not use predefined categories or assumptions.
• Base your segmentation only on observed patterns in the data.
• There is no single correct answer—focus on logical reasoning and justification.
Dataset
ID Preferred Age Purchase Income Online Spending Gender
Category Frequency (₹) Visits/Month Score
C1 Fashion 21 High 22000 25 90 F
C2 Electronics 23 Low 25000 22 85 M
C3 Fashion 25 Medium 30000 20 80 F
C4 Electronics 27 High 35000 18 75 F
C5 Beauty 29 High 40000 17 70 M
C6 Electronics 31 Low 45000 15 65 M
C7 Fashion 33 Medium 50000 14 60 F
C8 Home 35 Low 55000 13 55 M
C9 Beauty 37 High 60000 12 50 F
C10 Electronics 39 Medium 65000 10 45 F
C11 Home 41 Low 70000 9 40 M
C12 Electronics 43 Low 75000 8 35 F
C13 Beauty 45 High 80000 7 30 M
C14 Home 47 Medium 85000 6 25 M
C15 Fashion 49 High 90000 5 20 F
C16 Gaming 22 Low 23000 24 88 M
C17 Fashion 24 Medium 28000 21 82 F
C18 Electronics 26 High 32000 19 78 M
C19 Beauty 28 Low 36000 18 72 F
C20 Home 30 Medium 42000 16 68 F
C21 Fashion 32 High 48000 15 62 M
C22 Electronics 34 Low 52000 14 58 F
C23 Beauty 36 Medium 58000 13 52 M
C24 Electronics 38 High 62000 11 48 M
C25 Home 40 Low 68000 10 42 F
C26 Electronics 42 Medium 72000 9 38 M
C27 Beauty 44 High 77000 8 34 F
C28 Home 46 Low 82000 7 28 F
C29 Fashion 48 Medium 87000 6 24 M
C30 Electronics 50 High 92000 5 18 F
C31 Fashion 21 Low 24000 26 92 M
C32 Gaming 23 Medium 26000 23 87 F
C33 Beauty 25 High 31000 21 83 M
C34 Electronics 27 Low 34000 19 77 M
C35 Fashion 29 Medium 39000 18 73 F
C36 Home 31 High 44000 16 67 F
C37 Beauty 33 Medium 49000 15 61 M
C38 Electronics 35 Low 54000 14 56 F
C39 Fashion 37 High 59000 13 51 M
C40 Electronics 39 Medium 64000 11 46 F
C41 Beauty 41 Low 69000 10 41 M
C42 Home 43 High 74000 9 36 F
C43 Fashion 45 Medium 79000 8 31 M
C44 Electronics 47 Low 84000 7 27 F
C45 Beauty 49 High 89000 6 22 M
C46 Gaming 22 Medium 21000 27 95 F
C47 Fashion 26 Low 33000 20 79 M
C48 Electronics 30 High 47000 17 66 F
C49 Beauty 34 Medium 53000 14 57 M
C50 Home 38 Low 61000 12 49 F