Customer Segmentation using RFM Analysis and K-Means Clustering

Project Overview

This project performs customer segmentation on the Online Retail dataset using RFM (Recency, Frequency, Monetary) analysis and K-Means clustering.

The objective is to identify different customer groups based on purchasing behavior and provide actionable business insights.

Dataset

Online Retail Dataset

Features include:

• Invoice Number
• Product Information
• Quantity
• Invoice Date
• Unit Price
• Customer ID
• Country

Technologies Used

• Python
• Pandas
• NumPy
• Matplotlib
• Seaborn
• Scikit-learn
• Jupyter Notebook

Methodology

1. Data Cleaning
2. Feature Engineering
3. RFM Analysis
4. Data Scaling
5. Elbow Method
6. K-Means Clustering
7. Customer Segmentation
8. Business Insights

Customer Segments

• Champions
• VIP Customers
• Loyal Customers
• Lost Customers

Visualizations

1. Elbow Method

The Elbow Method was used to determine the optimal number of clusters for K-Means clustering.

---

2. Customer Distribution by Segment

This chart shows the number of customers in each identified segment.

---

3. Customer Segments based on Frequency and Monetary Value

The scatter plot visualizes customer groups based on purchase frequency and spending behavior.

---

4. Monetary Value by Segment

This visualization compares the spending patterns of customers across segments.

Key Insights

• Champions are the most valuable customers.
• VIP customers contribute significant revenue.
• Loyal customers provide consistent business.
• Lost customers require re-engagement strategies.

Conclusion

Customer segmentation helps businesses understand customer behavior, improve retention, and design targeted marketing campaigns.