A series of Ipython notebooks and python code to show prototypes of recommenders.


Recommender POCs

  • This repo is a prototype of different recommendation algorithms.
    • Movies Collaborative Filtering
    • Movies SVD Matrix Factorization
    • Movies non-personalized recommendation
    • Beer Reccommender
    • Association rules
    • An overview over recommenders with code
    • It contains also examples of the recommendation we've built for migros.
    • It contains an Import of google transaction data for recommendations.
    • It contains sample data:
      • movies
      • beer
    • online retail example

Link to DEMO or 30s VIDEO of the project


  • What is the benefit for the customer: A user gets recommended items.
  • What is the benefit for the business: A business owner can sell more items or show more relevant items.


  • How much MD did you use to build it: 10MD


  • Which data is it based on: Different datasets.

Used Technologies

  • Which technologies were used: scikit learn, SVD, pandas


  • Which things could be build with this POC if you had more time: Integrate them in production systems, like we did for