On Sat, 17 Apr 2004 15:39:34 -0400, Alex Farberov
<[EMAIL PROTECTED]> wrote:

> Hey,
> 
> I need an algorithm similar to amazon.com which would give me n items 
> that were rated highest by the users that rated item x high. i.e. people 
> who liked this book also liked those 5..
> 

Doesn't Amazon just give you the items that were 
*purchased*? - so they can settle for crosstabulation.

I suppose that if there are ratings, you can use Pearson
correlation.  If it is at all like Amazon, the number of
items is huge while the number of rating is small.

[ snip, rest]

-- 
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to