A patent application titled “Content personalization based on actions performed during a current browsing session” by five inventors at Amazon has recently been published. The patent was filed in January 2002.
The present invention provides methods for recommending items to users without requiring the users to explicitly rate items or create lists of their favorite items. The personal recommendations are preferably generated using item relatedness data determined using the above-mentioned methods, but may be generated using other sources or types of item relatedness data (e.g., item relationships determined using a content-based analysis). In one embodiment (described below), the personalized recommendations are based on the web pages or sites viewed by the customer during a current browsing session, and thus tend to be highly relevant to the user’s current browsing purpose.
While I find Amazon’s recommendation system interesting, their recommendations seldom seem to connect the dots in a way that gets me to actually purchase something other than what I came in looking for. On the other hand, I’m sure this is something that improves significantly with time as they perfect their algorithms and as they accummulate an ever increasing collection of my personal history information (what I browsed, what I searched for, what I bought, what I sold, etc.)
Slashdot picks up the discussion.