We use cookies

Essential cookies keep this site running. With your consent, we'll also use analytics and marketing cookies to improve your experience. See our Privacy Policy.

Cookie settings

Choose which cookies we can use. Essential cookies are always on because the site can't work without them. Your choice is saved for 6 months.



Goal

Drive revenue through recommendations sent using email channel and improve understanding of customer needs to drive demand based production of new products

Challenge

All subscriber and marketing data was held in an excel file that frequently crashed. It was impossible to do effective customer segmentation, clustering, & analytics.

Solution

  • The model we created leveraged subscriber, purchasing, marketing, and website data to generate recommendations for items add ons to boxes and subscription upselling using deep learning techniques.
  • Built out their data warehouse (Snowflake), marketing analytics capabilities, and a web app for new marketing workflows in AWS.
  • The system not only dynamically created new unique boxes but also drove the production of new products based on demand from customers.

Results

Once deployed, our system increased revenue by 20%