Customer Segmentation Analysis 🚀

🚀 Python🐍 Unsupervised Machine Learning🧠 Data Analysis📊

Table of Contents 📚

• Project Overview
• Data Summary
• Exploratory Data Analysis
• Unsupervised Machine Learning Algorithms
• Results and Insights
• Conclusion

Project Overview🔍

Customer Segmentation is a crucial business practice that involves grouping customers based on shared characteristics. This analysis leverages unsupervised machine learning to classify customers using behavioral and demographic data.

The insights help businesses:

• Target specific customer groups effectively.
• Enhance marketing strategies tailored to customer preferences.
• Boost customer satisfaction and loyalty.

Data Summary📂

The dataset comprises 2,000 customer records from an FMCG store, captured through loyalty card transactions. It includes 8 key features providing demographic and behavioral insights.

Feature	Description	Values
ID	Unique identifier for each customer.	Alphanumeric
Sex	Gender of the customer.	0: Male, 1: Female
Marital Status	Marital status of the customer.	0: Single, 1: Non-Single
Age	Age of the customer.	Integer (Years)
Education	Highest level of education attained.	0: Other, 1: High School, 2: University, 3: Graduate School
Income	Self-reported annual income (USD).	Integer (e.g., 25000, 50000, 75000)
Occupation	Customer’s job category.	0: Unemployed, 1: Skilled, 2: Management/Self-Employed
Settlement Size	Type of city the customer resides in.	0: Small, 1: Mid-Sized, 2: Big City

Exploratory Data Analysis(EDA)🔍

1️⃣ Age Distribution:

• Visualized the age spread of customers across different regions.

2️⃣ Income Patterns:

• Analyzed income disparities based on education and occupation.

3️⃣ Gender Segmentation:

• Examined purchasing patterns for male and female customers.

4️⃣ Regional Insights:

• Compared settlement sizes to identify trends in small, mid-sized, and big cities.

Unsupervised Machine Learning Algorithms 🤖

🔹 Hierarchical Clustering:

• Groups customers into a dendrogram structure to reveal natural clusters.
• Provides insights into similar customer segments.

🔹 K-Means Clustering:

• Partition-based algorithm for segmenting customers into ‘K’ distinct clusters.
• Ideal for identifying prominent customer groups with similar spending habits.

🔹 PCA (Principal Component Analysis):

• Reduces dataset dimensions while retaining maximum variance.
• Simplifies data visualization and improves clustering accuracy.

Results and Insights☀️

1. Key Clusters Identified:

• High-income customers in big cities with graduate-level education.
• Budget-conscious customers from small cities.
• Mid-income customers prefer mid-sized cities.

2.Demographic Breakdown:

• Majority of the customers are aged between 25-45 years.
• Females showed a higher representation in the high-income segment.

3.Regional Insights:

• Big cities contribute to 60% of high-value purchases, while small cities show a preference for budget-friendly options.

4. Education and Spending Patterns:

• Graduate school customers demonstrated higher annual spending, while high school graduates leaned towards cost-efficient products.

Conclusion

The segmentation revealed actionable insights for tailoring marketing strategies, such as:

• Launching premium product campaigns for high-income clusters.
• Promoting value-based offerings in small city segments.
• Designing personalized loyalty programs for mid-income customers.

These findings empower businesses to drive customer-centric growth strategies and ensure sustainable profitability.

Connect🤝

• 📩 Email: kshitijachilbule5@gmail.com
• 👩‍💻 Github: https://github.com/itskshitija
• 📶 LinkedIn: https://www.linkedin.com/in/kshitija-chilbule-b98515309/
• 🌐 Portfolio: https://itskshitija.github.io/My-Portfolio/