News for hackers. Stuff that matters.
Re:Two Decades of Recommender Systems at Amazon.com by DonaldFisk on Wednesday July 05, 2017 @09:07PM (#14707447)
That sucks.

The problem is that the algorithm seems to be unable to distinguish interchangeable items (e.g. vacuum cleaners, lawnmowers, Swiss Army knives) which you need exactly one of, similar items (e.g. different death metal albums, or Hammer horror movies) which if you bought one of, you'll probably want some others, and connected items (e.g. different parts of a course) where you'll probably want all the others.

Re:Two Decades of Recommender Systems at Amazon.com by icebraining on Thursday July 06, 2017 @02:58AM (#14708634)
It's weird, though; seems like an "average time between purchases" associated with each category would be an obvious metric to use in the algo.
Re:Two Decades of Recommender Systems at Amazon.com by TeMPOraL on Thursday July 06, 2017 @05:31AM (#14709116)
A small problem might be that they're probably trying to optimize that metric, i.e. reduce your average time between purchases in each category...
Re:Two Decades of Recommender Systems at Amazon.com by andrewingram on Thursday July 06, 2017 @05:02AM (#14709011)
Some fungibility factor attached to each product wouldn't be amiss here