Retail

Dynamic price optimization for an Apparel and Lifestyle Retailer boosting customer churn by 80%

About the Client

Multi-national America-based clothing manufacturer, distributor, and retailer catering with 20000+ SKU to their customers across globe.

The Challenge

With traditional approach of data analysis, client was facing difficulty to set up unique pricing for their premium customer to support the product pricing decisions by defining a Dynamic Pricing policy using machine learning for managing dynamic pricing for an ever-increasing inventory of SKUs in a competitive environment.

What We Did

  • Data Acquisition
  • Predictive Analysis
  • Classification
  • Data Cleansing
  • Optimization
  • RFM Analysis
  • Clustering
  • Deep Learning
  • Data Acquisition
  • Predictive Analysis
  • Data Cleansing
  • Optimization
  • Clustering
  • Deep Learning
  • Classification
  • RFM Analysis

The Solution

DX Factor’s in-house team of Data scientists and Machine learning engineer built and deployed a dynamic pricing model that suggest right product pricing policy.

The objective behind this solution is to make sure relevant data is available to Merchant in real-time.

  • Created a pricing policy based on consumer behaviour, medium performing SKUs.
  • This pricing model automatically suggests the right product pricing policy and selecting the most rewarding one for real world scenarios.
  • Developed a price prediction model through user feedback, RFM analysis, historical pricing.
  • The application’s algorithm monitors characteristics like item’s category, quality, product description, usage, availability, shipping cost and type and then predict the appropriate price.

Results & Outcomes

DXFactor revolutionized the Merchant’s data strategy by making it more dynamic and results oriented. The client has now tasked us to extend this solution to their sub-vendors.

100%

transparency with Customer Behaviour Insights

45%

accuracy in estimation of pricing adjustment based on target and audience

85%

boost in customer engagement with predictive model built