RFM Analysis for E-Commerce Customer Segmentation

01 / Process

How the work unfolded

This project was part of an assignment for the Laskar AI bootcamp to create an interactive data analysis application. The process involved several key stages:

1. Data Collection & Cleaning: The e-commerce transaction data was first cleaned to handle missing values, duplicates, and other anomalies to ensure the accuracy of the analysis.
2. RFM Metric Calculation:
   • Recency (R): Calculating when a customer last made a transaction.
   • Frequency (F): Calculating how often a customer makes a purchase within a specific period.
   • Monetary (M): Calculating the total monetary value spent by a customer.
3. Customer Segmentation: After calculating the RFM metrics, each customer was assigned a score (e.g., on a 1-5 scale) for each metric. Based on the combination of R, F, and M scores, customers were grouped into segments such as "Best Customers," "Potential Loyalists," "At Risk," or "Lost Customers."
4. Visualization & Dashboard Development: The analysis and segmentation results were visualized using Matplotlib. All findings were then integrated into an interactive web dashboard built with Streamlit, allowing users to visually and dynamically explore the customer segment distribution.