Slashdot Mirror


New Amazon Patents on Content Personalization

theodp writes "Defending its decision to concoct recommendations to steer customers to buy items at Amazon's new Apparel Store, a spokeswoman said Amazon "felt it would be evident to people that since the store was so new, we wouldn't have the transaction history to create database similarities." But in this just-published patent applicaton, Amazon earlier told the USPTO it's able to use product viewing histories to determine the similarity or relatedness between products for which little or no purchase history data exists. So which claim should you believe?"

3 of 88 comments (clear)

  1. clothes != books by js7a · · Score: 2, Interesting

    Anyone who thinks that product recommendation algorithms that work for books are going to work as well for clothes is in for a rude awakening.

  2. Does any of this mean that as a brick and mortar by kfg · · Score: 3, Interesting

    salesman I can patent watching my customers browse and trying to get them to buy things based on what I observe them looking at?

    Man, am *I* going to clean up. Every salesman in the universe who's even vaguely doing their job is going to owe me a royalty.

    Hell, I might even be able to afford paying the royalty on the P&B sandwich I have for lunch now.

    KFG

  3. Re:Don't be silly. by Anonymous Coward · · Score: 1, Interesting

    The idea that you can tell what kind of clothes people will like from their book buying habits without any previous purchasing information obviously not going to work.

    All marketers believe contrary. Knowledge of your previous buying habits (regardless of where the history data comes from) gives clues as to your personality type, target demographics, and future product decisions. It could even be argued that data gathered about the reading material you've purchased is especially juicy info as it would be a more "direct line" on your personality traits and buying habits.