Online advertising creative tips
Document Actions
Amazon.com Amazon personalized recommendations - collaborative filtering
Fairly technical paper describing how Amazon does its famous collaborative filtering or personalized product recommendations on its website and within Emails.
Amazon's Recommendations / Personalization system certainly isn't new, people have used Amazon's "Customers Who bought X"... as an example of how to personalise for years. But I found this paper outlining HOW they do it while doing some research.
On my site, you can also read a Amazon.com case study
This is Amazon’s signature feature. Everyone mentions it as best practice when discussing web-based personalisation.
This paper summarises how it works by an Amazon insider.
According to Matt Round talking at E-metrics, 2004:
- It relies on crunching massive data volumes: Every page, every search, every purchase
- Requires techniques for sifting patterns from noise
- Two other successful features: Customers who shopped for X also SHOPPED for… Customers who searched for X also BOUGHT…
Please bookmark this article if you found it useful (just two clicks).
Please add your comments, experiences or link suggestions to inform me and other visitors to my site.
I've set it up to be quick, but you can't add true hyperlinks - just text.
Thanks, Dave Chaffey.
