<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:georss="http://www.georss.org/georss" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:media="http://search.yahoo.com/mrss/"
		>
<channel>
	<title>Comments on: Amazon Recommendation Algorithm Gone Mad?</title>
	<atom:link href="http://socialmode.com/2009/10/23/amazon-recommendation-algorithm-gone-mad/feed/" rel="self" type="application/rss+xml" />
	<link>http://socialmode.com/2009/10/23/amazon-recommendation-algorithm-gone-mad/</link>
	<description>Integrated Synthesis of Media, Society and Behavior</description>
	<lastBuildDate>Sat, 10 Mar 2012 15:47:05 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.com/</generator>
	<item>
		<title>By: un1crom</title>
		<link>http://socialmode.com/2009/10/23/amazon-recommendation-algorithm-gone-mad/#comment-1800</link>
		<dc:creator><![CDATA[un1crom]]></dc:creator>
		<pubDate>Wed, 17 Mar 2010 16:19:42 +0000</pubDate>
		<guid isPermaLink="false">http://socialmode.com/?p=1384#comment-1800</guid>
		<description><![CDATA[thanks for linking the paper!

yer quite right.... it&#039;s probably the best way (business reasons) to do it.]]></description>
		<content:encoded><![CDATA[<p>thanks for linking the paper!</p>
<p>yer quite right&#8230;. it&#8217;s probably the best way (business reasons) to do it.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Elf M. Sternberg</title>
		<link>http://socialmode.com/2009/10/23/amazon-recommendation-algorithm-gone-mad/#comment-1799</link>
		<dc:creator><![CDATA[Elf M. Sternberg]]></dc:creator>
		<pubDate>Wed, 17 Mar 2010 16:17:02 +0000</pubDate>
		<guid isPermaLink="false">http://socialmode.com/?p=1384#comment-1799</guid>
		<description><![CDATA[If you&#039;ve ever read &lt;a href=&quot;http://www.cs.umd.edu/~samir/498/Amazon-Recommendations.pdf&quot; rel=&quot;nofollow&quot;&gt;Amazon&#039;s Recommendation Engine&lt;/a&gt; paper, you would see that their claim is quite literal.  People who bought whatever it is that you have bought in the past also immediately bought the items listed.   

It&#039;s not even based on &quot;people like you.&quot;  It&#039;s quite literal: objects in your &quot;recently bought&quot; list have, as immediate or concurrent purchases by the same person, those objects listed above.  The relationship is strong enough that Amazon regularly gets impulse buys out of showing you that list.]]></description>
		<content:encoded><![CDATA[<p>If you&#8217;ve ever read <a href="http://www.cs.umd.edu/~samir/498/Amazon-Recommendations.pdf" rel="nofollow">Amazon&#8217;s Recommendation Engine</a> paper, you would see that their claim is quite literal.  People who bought whatever it is that you have bought in the past also immediately bought the items listed.   </p>
<p>It&#8217;s not even based on &#8220;people like you.&#8221;  It&#8217;s quite literal: objects in your &#8220;recently bought&#8221; list have, as immediate or concurrent purchases by the same person, those objects listed above.  The relationship is strong enough that Amazon regularly gets impulse buys out of showing you that list.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

