Efficient product loading in direct to retail distribution channel


A leading consumer goods manufacturer has a direct to retail distribution model in a market – load products on vans from their warehouses and sell directly to retailers. The client had deployed a model to predict the necessary loading for all products for all sales agents across sales offices. However, it was observed that the quantum of unloads at the end of the sales run was high. Consequently, the client wanted to leverage machine learning to optimize loading and reduce loading/unloading time and manpower cost

Efficient Product Loading In Directo to Retail


Business Understanding

We collaborated with sales and distribution teams to understand the business model in detail and draw up a holistic list of parameters which might impact the retail demand and consequently the loading

Feature Engineering

Features were generated for the following class of demand impact factors:

  • Historical purchase pattern of the retailer for each product
  • Pricing variations due to permanent price changes and short terms promotions
  • Holiday and festival linked demand variations
  • Impact of weather on the retail demand

Model Development

To predict the retail demand for each product for each sales agent on a particular day, two models were applied in sequence:

  • Purchase Predictor: Classification model which predicts whether a retailer will buy a particular product on a day based on the identified features
  • Quantity Predictor: Model predicts the quantum of each product a retailer will purchase, if purchase predictor predicts that the retailer will purchase


  • Reduced unloading percentage by ~10% across 4 sales offices
  • Carton movement (effort for stock loading and unloading) was reduced by 20-30% across the four sales offices
  • Stock shortages measured as percentage of days where the van returned with no stock was maintained at levels amenable for business

Case Studies