An end-to-end Customer Retention Analytics project built in Microsoft Power BI that transforms raw Adidas retail data into interactive dashboards and actionable business insights.
The project analyses customer churn, loyalty program effectiveness, repeat purchase behaviour, store performance, customer lifetime value (CLV), and customer segmentation to support data-driven retention strategies.
🎥 Includes a complete walkthrough video explaining the dashboard, data model, DAX measures, insights, and business recommendations.
Customer retention is one of the most important drivers of long-term business growth. Adidas operates through multiple retail channels, franchise stores, flagship stores, and e-commerce platforms while managing a large customer base and loyalty program.
This project consolidates customer demographics, purchase history, loyalty information, store performance, and churn data into an interactive Power BI dashboard that helps identify customer behaviour patterns and provides strategic recommendations for improving retention and profitability.
- 📊 Multi-page interactive Power BI dashboard
- 🧹 Data transformation using Power Query
- 📈 DAX measures and KPIs
- 📉 Customer churn analysis
- 💰 Customer Lifetime Value (CLV) analysis
- 🛍️ Store and channel performance evaluation
- 🎯 Customer segmentation
- 💡 Executive recommendations
- 🎥 Complete dashboard walkthrough video
- 💼 Portfolio-ready documentation
- Build a robust customer retention dashboard
- Analyse customer churn across multiple dimensions
- Evaluate loyalty program effectiveness
- Identify repeat purchase behaviour
- Compare store and online channel performance
- Calculate Customer Lifetime Value (CLV)
- Segment customers by purchasing behaviour
- Deliver actionable business recommendations
- Microsoft Power BI Desktop
- Power Query
- Data Modelling
- Relationships
- DAX Measures
- Calculated Columns
- KPI Cards
- Interactive Slicers
- Drill-down Analysis
- Multi-page Dashboards
- Customer Analytics
- Customer Retention Analysis
- Churn Analysis
- Business Intelligence
- KPI Reporting
- Customer Segmentation
- Dashboard Design
- Data Visualization
The project uses multiple Adidas retail datasets, including:
- Customer Demographics
- Customer Transactions
- Store Locations
- Loyalty Program
- Churn Labelled Customers
The dashboard combines these datasets into a unified data model for comprehensive customer analysis.
Provides a high-level overview of customer retention performance using key business metrics.
- Churn Rate
- Retention Rate
- Average Customer Lifetime Value
- Repeat Purchase Rate
Evaluates how promotions and loyalty programs influence customer engagement and purchasing behaviour.
- Promotion Percentage
- Average Purchase Amount
- Churn Rate by Loyalty Tier
- Points Earned vs Redeemed
- Promotions increase average transaction value.
- Elite customers show the highest churn rate.
- Loyalty points redemption remains significantly underutilized.
Compares performance across different store types and sales channels.
- Average Transaction Amount
- Churn Rate by Store Type
- Retention vs Store Opening Year
- Franchise and Outlet stores generate higher average transaction values.
- Flagship stores exhibit the highest customer churn.
- Older stores demonstrate slightly better customer retention.
Segments customers based on purchasing behaviour and lifetime value.
- Total Customers
- Repeat Customers
- Churned Customers
- High Value Customers
- Low CLV
- Medium CLV
- High CLV
- Most customers belong to the Low CLV segment.
- Repeat customers form a significant portion of the customer base.
- High-value customers require focused retention strategies.
Summarises the business findings into actionable recommendations.
- Prioritize retention of high-value and repeat customers.
- Improve customer experience in flagship stores.
- Increase loyalty point redemption through personalized incentives and simplified rewards.
- Customer churn remains relatively high, highlighting the need for stronger retention initiatives.
- Loyalty tiers influence purchasing behaviour and retention.
- Promotions positively impact transaction value.
- Flagship stores require focused retention improvements.
- Customer Lifetime Value varies significantly across customer groups.
- Personalized loyalty incentives can improve customer engagement.
A complete walkthrough video explaining the project is available below.
👉 Project Demonstration Video
https://www.loom.com/share/c8640f05c0b6495fbcbc637c77618d9f
The walkthrough includes:
- Project overview
- Data modelling
- Power Query transformations
- Dashboard pages
- DAX measures
- Business insights
- Executive recommendations
Retail-Customer-Retention-Analytics-PowerBI
│
├── dashboard
│ └── Retail_Customer_Retention_Analytics.pbix
│
├── datasets
│ ├── Customer_Demographics.csv
│ ├── Customer_Transactions.csv
│ ├── Store_Locations.csv
│ ├── Loyalty_Program.csv
│ └── Churn_Labelled_Customers.csv
│
├── report
│ └── Retail Customer Retention Analytics.pdf
│
├── screenshots
│ ├── page1_executive_dashboard.png
│ ├── page2_loyalty_promotion.png
│ ├── page3_store_channel_analysis.png
│ ├── page4_customer_segmentation.png
│ └── page5_executive_recommendations.png
│
├── README.md
└── LICENSE
git clone https://github.com/YOUR_USERNAME/Retail-Customer-Retention-Analytics-PowerBI.git- Microsoft Power BI
- Power Query
- Data Modelling
- DAX
- Customer Analytics
- Churn Analysis
- Customer Segmentation
- Customer Lifetime Value (CLV)
- Dashboard Design
- KPI Reporting
- Business Intelligence
- Data Visualization
Sujal Agrahari
Artificial Intelligence & Machine Learning Undergraduate
Dr. Ambedkar Institute of Technology, Bengaluru
This project was developed as part of the Data Science training provided by Internshala Trainings.
The project requirements and datasets were provided during the training, while the complete dashboard design, data modelling, DAX calculations, visualizations, analysis, documentation, and business recommendations were independently developed by the author.
This repository is intended for educational and portfolio purposes. The datasets were provided as part of the training, while the dashboard, analysis, insights, documentation, and recommendations were created by the author.
If you found this project useful or interesting, consider giving the repository a ⭐ Star.