Data Science in Business Insights for a retail chain
A leading retail chain with more than 1000+ stores and 800+ items. The chain sells items of top brands and they have their own brand too.
Client has more than 3 million customers with loyalty cards. Most of these customers were dormant. Customer dormancy was increasing and there was no visibility into it. They were having millions of transactions per month. The data ran into terabytes and was making it difficult to analyze and get customer insights. Client was unable to create some item baskets.
- The key goal was to improve customer retention, reduce dormancy % and make more and more loyalty cards active.
- This also included proving data for various campaigns.
- The objective was also to suggest some baskets to improve sales of items.
- Customer Insights across various parameters was needed.
- There was a need of Consumer Analytics techniques and Machine Learning algorithms.
- Scoring model has been created based on RFM.
- Dormancy classification was developed to identify customers which may become dormant based on purchase pattern and consumer information.
- Association rule mining was used to create market baskets which can be offered to the customers.
- Customer Insights has been provided on client’s choice of tool.
30% to 70% jump
Active customers increased from 30% to 70 %
3M to 8M subscriptions
Loyalty cards increased from 3 M to 8 M
Improved data insights
Targetted campaigns resulted in growth in sales and showed better customer insights.
Appreciate the service levels and the commitment shown by the team to address the business requirements and meeting the timelines.