Markdown Optimization to Drive Discount Sales, Minimizing the Impact on Brand and Profit Margins for a Top Athletic Apparel & Footwear Brand

Client

The client is a Germany-based multinational organization that sells athletic clothing, shoes, and accessories. It is the second largest sportswear producer in the world and the first producer in Europe.

Challenges

The retailers needed recommendations for optimal markdown for a range of articles based on accounting stock, profitability, and operating costs. This was necessary so that the business would not miss revenue opportunities and incur excess operational and inventory costs. A data science and AI/ML-led markdown optimization (MDO) solution was required to apply price elasticity and inventory optimization techniques for effective markdown planning in retail stores.

LTM Solution

• For solution designing, certain tech stacks were leveraged—Databricks for Data management, Python programming for AI/ML, and Microsoft Power BI for Delivery of Insights on Recommendations.
• A data science and AI/ML-led solution was deployed on Databricks Lakehouse for the North America (NAM) region. It was designed for use and scalability in other regions in the future. 
• The AI/ML solution was used to deploy analytical models and a rule engine that configured markdown and pricing optimization rules to derive recommendations. 
• A data management module was designed to extract and model baseline data from data sets like Sellout, Inventory, Price History, Article Season, and POV article list.

Business Benefits

• 8% increase in revenue, based on data science-led decision-making for markdown and discount sales
• Recommendations on the right articles for markdown and adjusting prices based on demand elasticity helped retailers sell more.
• Inventory optimization cleared slow-moving or perishable items and created shelf space for newer and more profitable items.
• Improved inventory turnover by offering the right discounts helped retailers achieve higher inventory turnover rates.