Trust & Recommendation Systems
April 11th, 2003
Howard Rheingold talks about a study that shows how recommendation systems — like Amazon’s “Customers who bought this book also bought…” or NetFlix’s “People who liked this movie also liked…” — can be shilled:
“Taken together, the experiments provide several tips for the designers of interfaces to recommender systems. Interfaces should allow users to concentrate on rating while ignoring predictions. Finer-grained rating scales are preferred over simple “thumbs up, thumbs down” scales, but are not essential to good predictions. Finally, because users are sensitive to manipulation and inaccurate predictions, to keep customers happy, no recommender system at all is better than a bad recommender system.”
Note to self: you’ve got some thoughts on recommendation systems. Don’t forget to post them soon…