Subscribe to:
Post Comments (Atom)
skip to main |
skip to sidebar
About Me
- Greg Linden
Subscribe to the Feed
More Geeking with Me
Blog Archive
-
▼
2006
(324)
-
▼
December
(17)
- Is desktop search over?
- Top Geeking with Greg in 2006
- Google makes 20 cents per search?
- Defining geek
- Five things about me
- Findory in the UK Guardian
- Talk on eBay architecture
- Property rights on your attention
- AlwaysOn panel: What is the data telling us?
- 35% of sales from recommendations
- My 2006 predictions: The results
- The RSS beast
- YouTube cries out for item authority
- Spam is ruining Digg
- Yahoo's reorg
- Slides from my talk at Stanford
- YouTube and the Google boodle
-
▼
December
(17)
This is Personal
I've had this blog for 19 years. The views here are my own. This is a personal blog.
6 comments:
The factual errors in that article are too numerous to count.
Are they?
The 35% number likely is accurate. Personalization was responsible for well more than 20% of sales when I left Amazon in 2002. I would be surprised if it was not even higher now.
However, the article does claim that Amazon only rebuilds the databases used for recommendations every month. My understanding is that they are rebuilt multiple times per week (and the recommendations any individual shopper sees change immediately on new ratings, clicks, or purchases), so I think that part is unaccurate.
Are there other inaccuracies?
Haven't you considered generalizing and out sourcing some of the technology behind Findory to do just that?
I'm curious: at what rate are recommended items purchased?
Specifically, if an Amazon user views a page with recommendations, what are the odds that a given recommended item is purchased by that user? 1%? 0.1%?
I think the web owners should try to provide platforms encouraging recommendation (including some stat capturing).
IMO recommendation is the best unit of measurement for quality.
Gabe, sorry, I do not have those numbers.
Eran, that is a good idea. I have been thinking about whether Findory should attempt to launch a recommendation web service. The idea would be that, given some content (news, weblog posts, podcasts, etc.), Findory would make recommendations for other interesting content (news articles, documents, advertisements, etc.).
Post a Comment