Provided a robust framework to predict the roll out of online grocery pickup service in stores, for one of the largest retailers in the US


The client wanted to launch online grocery pickup service as a competitive angle to counter the often pricier Online Grocery (OG) delivery services. Their plan was to roll out this initiative in a phased manner, by markets. To make the roll-out successful, they were looking for a solution that could provide intelligent recommendations on physical stores where OG should be rolled out.


Predictive analytics was performed to prescribe recommendations.

  • Key parameters were chosen from an exhaustive set of attributes such as OG data for existing stores, Point of Sales data, competitor information, market factors, and behavioural segments
  • Machine Learning techniques like GLM, Random Forest, and SVM were used to predict OG orders for new stores
  • Bootstrapping technique was implemented for model robustness
  • The algorithms were tested and validated recursively on 100 random samples
  • The model predictions improved over time

Key Benefits

  • The solution helped identify factors in?uencing OG orders such as the client’s grocery share in CMA, percentage of shoppers who fall under primary grocery households, grocery sales over the past 4 months, OG awareness in CBSA, etc.
  • Based on model predictions, the client was able to classify stores as super-high, high, and medium, allowing optimal budget allocation for rolling out OG in select stores


Icon Boost

Client has successfully rolled out OG in more than 600 stores

Icon Boost

Client was able to derive more pro?tability from OG customers, with purchases 27% more than similar in-store-only customers

Icon Boost

About 20% of store customers now have tried OG

Talk To Us