<?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/"
		>
<channel>
	<title>Comments on: Austin-Based Thoof Launches Private Beta</title>
	<atom:link href="http://www.austinstartup.com/2007/06/austin-based-thoof-launches-private-beta/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.austinstartup.com/2007/06/austin-based-thoof-launches-private-beta/</link>
	<description>Austin Technology News, Events, Opinions</description>
	<lastBuildDate>Fri, 19 Mar 2010 07:46:40 -0500</lastBuildDate>
	<generator>http://wordpress.org/?v=2.8.4</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: Zack McCoy</title>
		<link>http://www.austinstartup.com/2007/06/austin-based-thoof-launches-private-beta/comment-page-1/#comment-5</link>
		<dc:creator>Zack McCoy</dc:creator>
		<pubDate>Fri, 22 Jun 2007 18:03:23 +0000</pubDate>
		<guid isPermaLink="false">http://72.167.125.157/2007/06/21/austin-based-thoof-launches-private-beta/#comment-5</guid>
		<description>These suggestion algorithms are notoriously difficult, especially when you&#039;re trying to make them fast enough to calculate millions of suggestions. The problem isn&#039;t really the algorithm Netflix uses, it&#039;s the fact that people are boring. Netflix can only suggest things based on statistical trends they discover. The fact that they recommend every Julia Roberts movie after you rate one of them 3 stars is only because other people that see one Julia Roberts movie always watch (and like) all the others too. Maybe if you were more boring too...

PS. If you want to win a million dollars, improve the algorithm at www.netflixprize.com.
</description>
		<content:encoded><![CDATA[<p>These suggestion algorithms are notoriously difficult, especially when you&#8217;re trying to make them fast enough to calculate millions of suggestions. The problem isn&#8217;t really the algorithm Netflix uses, it&#8217;s the fact that people are boring. Netflix can only suggest things based on statistical trends they discover. The fact that they recommend every Julia Roberts movie after you rate one of them 3 stars is only because other people that see one Julia Roberts movie always watch (and like) all the others too. Maybe if you were more boring too&#8230;</p>
<p>PS. If you want to win a million dollars, improve the algorithm at <a href="http://www.netflixprize.com" rel="nofollow">http://www.netflixprize.com</a>.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
