Being accurate is not enough: how accuracy metrics have hurt recommender systems.

Sean M. McNee John Riedl Joseph A. Konstan

Published in: CHI Extended Abstracts (2006)

Keyphrases

recommender systems
high accuracy
highly accurate
precision and recall
high precision
error analysis
collaborative filtering
high quality
sufficiently accurate
recommendation algorithms
classification accuracy
computational cost
prediction accuracy
error rate
user feedback
cold start problem
case study