ML Based Optimization Model Of Merchandise Product Mix Using Neural Networks

ML Based Optimization Model Of Merchandise Product Mix
Using Neural Networks

The Challenge

Our client, a popular retailer in the United States, wanted to increase revenue from each of their stores by improving merchandise effectiveness in their physical stores . They wanted to determine what products should be introduced, stored, or discontinued at each store based on forecasted availability, revenue and profits from each product.

Hypothesis

  • Online sales are a good proxy for demographics within catchments of physical stores.
  • Sales of existing products, similar to a new product, can be used to forecast the sales potential of the new product and therefore make stocking decisions.

Execution

  • Team decided to estimate sales ratio of each SKU to identify gaps in the merchandise mix.
  • The ML model continuously optimizes the merchandize mix based on the correlation between product level demand forecasts and actual sales at individual stores.

Outcomes

  • Successful integration of stocking recommendations for each store.
  • The model show significant potential in improving the merchandise mix in the store leading to a significant increase in sales.

Project Highlights

23%

DECREASE IN “NO INVENTORY” ON PROMOTED PRODUCTS