Project Title

CUSTOMER-SEGMENTATION-USING-RFM-ANALYSIS

Description:

This project leverages RFM (Recency, Frequency, Monetary) analysis to segment customers of an eCommerce platform, sourced from a Kaggle dataset covering transactions from 2010 to 2011. Our objective is to enhance marketing strategies and customer retention by categorizing customers based on their purchasing behavior. Through meticulous data preprocessing, calculation of RFM metrics, and K-Means clustering, we identify distinct customer segments, each with unique purchasing patterns.

Objectives:

1. To preprocess eCommerce transaction data for RFM analysis.
2. To calculate RFM metrics for each customer.
3. To segment customers using K-Means clustering based on RFM metrics.
4. To provide tailored marketing strategies for each segment to boost retention and revenue.

Data Source:

The dataset, hosted by the UCI Machine Learning Repository, contains transactions from a UK-based online retail store, spanning from December 2010 to December 2011. It includes data on orders, products, customers, and transactions. Data Source : https://www.kaggle.com/datasets/carrie1/ecommerce-data

Methodology:

1. Data Preprocessing: Initial data cleaning, handling missing values, and data transformation to prepare the dataset for analysis.
2. RFM Metric Calculation: Computation of Recency, Frequency, and Monetary values for each customer to understand purchasing behavior.
3. Customer Segmentation: Application of K-Means clustering to segment customers based on their RFM scores.
4. Segment Profiling and Marketing Recommendations: Analysis of each customer segment to identify unique characteristics and formulate targeted marketing strategies.

Key Findings:

1. Identification of key customer segments with distinct purchasing behaviors.
2. Insights into the correlation between customer segments and their contribution to revenue.
3. Development of tailored marketing strategies for different segments to enhance customer engagement and profitability.

Limitations and Future Work:

Discusses the limitations encountered, such as the absence of customer feedback data, and outlines future directions for incorporating additional datasets, predictive modeling, and dynamic RFM segmentation.

Conclusion:

1. The project demonstrates the effectiveness of RFM analysis in understanding customer behavior and guiding targeted marketing efforts.
2. The findings provide a basis for enhancing customer satisfaction and driving business growth.