Recommender System for the Vorwerk Thermomix®

Development and operation of a recommendation system for Cookidoo - The recipe platform for Thermomix
/
Users cook often and regularly with their Thermomix, thanks to recipe recommendations that suit their tastes and lifestyle.
Increased user satisfaction through recipe recommendations that inspire users to think outside the box and try new recipes
/
Efficient delivery of personalised recommendations to more than 3 million users
Increase user engagement by up to 110 %

Challenge

  • Maximise paid Cookidoo subscriptions by inspiring recipe recommendations that inspire users to cook regularly with the Thermomix.
  • Increase in Thermomix sales through "word-of-mouth marketing" thanks to greatly improved user satisfaction with Cookidoo

Solution

  • A modern recommendation system built on cooking interactions based on machine learning algorithms from the field of collaborative filtering and content-based filtering.
  • Building ETL and machine learning pipelines, as well as a serving infrastructure to efficiently provide recommendations to more than 3 million users worldwide.
  • Operation, maintenance and continuous improvement of the productive recommendation application using a modern DevOps approach.

Result

  • Increase user engagement (click-through rate) by up to 110 %, measured in A/B tests
  • The recommended recipes are among the top clicked items on the platform

Are you interested in your own use cases?

Challenge

An automotive company would like to visualise various market-specific data in order to create a Competitive analysis for the US market.

Solution

There will be a interactive and Flexible application, including of different maps with two different views implemented.

Result

Relevant markets are identifies, analyses and visualises. The dealer or the respective sales department have the possibility to compare the direct competition with their own product and to visualise the relevant data.