Recommendation Algorithm Wants To Show You Something New

by SteveBayle on February 26, 2010

Accuracy has long been the most prized measurement in recommending content, like movies, links, or music. However, computer scientists note that this type of system can narrow the field of interest for each user the more it is used. Improved accuracy can result in a strong filtering based on a user’s interests, until the system can only recommend a small subset of all the content it has to offer.”

Nick Negroponte of the MIT Media Lab made this observation many years ago when they were experimenting with a totally personalized newspaper. One important human function is “discovery”. People like to discover new things, they like to share their discoveries, novelty is an enduring human value.  So naturally if you over filter in a recommendation engine you will greatly diminish the opportunities for discovery. 

Much as I love and use Amazon, I love bookstores and libraries as much or more, as I enjoy browsing and serendipitously discovering new books, DVDs or CDs. In fact, as a child who went to the library weekly with my parents, I quickly discovered that the carts with recently returned books were a great place to browse – an analog form of collective filtering.

When it comes to shopping we need to keep the values of novelty, discovery, browsing, and serendipity in front of us if we want shoppers using our applications to be engaged, excited and motivated to share their shopping experiences.

Posted via email from PostVerbela

Share and Enjoy:
  • Twitter
  • Facebook
  • Print
  • Digg
  • Sphinn
  • Mixx
  • Google Bookmarks
  • Suggest to Techmeme via Twitter
  • Technorati
  • Tumblr

Leave a Comment

Powered by WP Hashcash

Previous post: Bergdorf Goodman enters mobile commerce

Next post: Cellphone Applications Let Shoppers Point, Click and Buy –