Getting to know you - learning new user preference in recommender systems


  • Experimental design
    • Goal: Measure the effectiveness of the signup process
    • Metrics:
      • User effort - How hard was it to sign up
      • Accuracy - How well can the system make recommendations to the users
    • Reults
      • Random/Classique perform worst
      • Popularity, (log) Popularity * Entropy, Item-Item personalized strategies give the reasonable performance on both metrics

Evaluation of strategies over both experiments on user effort and accuracy metrics


A. M. Rashid et al., “Getting to know you: learning new user preferences in recommender systems,” in Proceedings of the 7th international conference on Intelligent user interfaces  - IUI ’02, San Francisco, California, USA, 2002, p. 127. doi: 10.1145/502716.502737.

#recommender-system #recommender-system/cold-start