Skip to content

mwang-cmn/Customer-Segmentation-Cohort-analysis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

Customer-Segmentation-Cohort-analysis

Read full Article - Here

Python Notebook - Here

This repository contains a comprehensive analysis of customer retention and purchasing behavior for an e-commerce platform. The analysis utilizes cohort analysis to track customer behavior over time, providing valuable insights for improving marketing strategies and customer retention efforts.

Introduction

Understanding customer behavior is critical for any business aiming to enhance customer retention and drive growth. This project conducts a time-based cohort analysis to segment customers based on their initial purchase dates and track their engagement over time. By analyzing retention rates, average purchase quantities, and overall engagement, we can tailor strategies to meet the specific needs of different customer groups.

Dataset Description

The dataset includes detailed transactional records from an e-commerce platform, containing the following columns:

  • InvoiceNo: Unique identifier for each transaction.
  • InvoiceDate: Date and time of the transaction.
  • CustomerID: Unique identifier for each customer.
  • StockCode: Unique identifier for each product.
  • Description: Brief description of the product.
  • Quantity: Number of units of the product purchased.
  • UnitPrice: Price per unit of the product.
  • Country: Country where the customer resides.

Key Insights

  1. Retention Rates: Range between 20% and 40%, indicating a significant portion of customers return to make purchases.
  2. December 2010 Cohort: Shows a retention rate above 30%, highlighting effective engagement strategies.
  3. December 2011 Drop: Noted a decline in retention rates, suggesting the need to investigate potential issues during that period.
  4. Retention Variability: Retention rates vary from 8% to 50%, indicating diverse customer behaviors.
  5. Stable Average Quantity: Despite fluctuations in retention, sales volume remains steady, suggesting fewer customers purchase larger quantities.

Recommendations

  1. Identify Factors Driving High Retention: Analyze the successful strategies of the December 2010 cohort and replicate them for other cohorts.
  2. Investigate December 2011 Drop: Investigate and address the causes behind the low retention rates in December 2011.
  3. Set Realistic Targets: Set retention targets based on historical data and industry benchmarks, aiming for gradual improvement.
  4. Implement Retention Strategies: Develop personalized marketing, loyalty programs, and targeted communication to enhance retention.
  5. Continuously Monitor and Adapt: Regularly analyze cohort data to adapt strategies and improve retention.
  6. Target High-Quantity Regions: Focus marketing efforts on countries with higher sales quantities, such as Tunisia, South Africa, Rwanda, and Somalia.

About

Time-Based Cohort Analysis for Customer Segmentation in Python

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published