<?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:go='http://ns.gigaom.com/'
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: Goombah: More music discovery</title>
	<atom:link href="http://gigaom.com/2006/11/27/goombah-more-music-discovery/feed/" rel="self" type="application/rss+xml" />
	<link>http://gigaom.com/2006/11/27/goombah-more-music-discovery/</link>
	<description></description>
	<lastBuildDate>Sat, 11 Feb 2012 12:44:45 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.com/</generator>
	<item>
		<title>By: Diane Sammer</title>
		<link>http://gigaom.com/2006/11/27/goombah-more-music-discovery/#comment-128698</link>
		<dc:creator><![CDATA[Diane Sammer]]></dc:creator>
		<pubDate>Mon, 27 Nov 2006 21:24:39 +0000</pubDate>
		<guid isPermaLink="false">http://gigaom.wordpress.com/2006/11/27/goombah-more-music-discovery/#comment-128698</guid>
		<description><![CDATA[&lt;p&gt;I am CEO of Emergent Music, the company that has developed Goombah.  As Liz has pointed out, we have taken a very different approach to music recommendations.  Goombah uses each user&#039;s desktop CPU to process the large quantities of data necessary to produce very good recommendations.  The 38.1 MB it takes on disk is mostly data that Goombah analyzes to calculate the best matching members for each user.  We like to say that it creates the perfect word-of-mouth network for each user.  It&#039;s a lot of data because it takes into consideration the entire music collection of each user when searching for the best matches.&lt;/p&gt;

&lt;p&gt;Goombah also gives users the ability to do targeted searches by playlist, specific tracks and favorite artists -- all modified by their chosen level of adventurousness. &lt;/p&gt;

&lt;p&gt;We believe that this approach results in recommendations of both people and music that are more accurate, interesting and full of surprises.&lt;/p&gt;]]></description>
		<content:encoded><![CDATA[<p>I am CEO of Emergent Music, the company that has developed Goombah.  As Liz has pointed out, we have taken a very different approach to music recommendations.  Goombah uses each user&#8217;s desktop CPU to process the large quantities of data necessary to produce very good recommendations.  The 38.1 MB it takes on disk is mostly data that Goombah analyzes to calculate the best matching members for each user.  We like to say that it creates the perfect word-of-mouth network for each user.  It&#8217;s a lot of data because it takes into consideration the entire music collection of each user when searching for the best matches.</p>
<p>Goombah also gives users the ability to do targeted searches by playlist, specific tracks and favorite artists &#8212; all modified by their chosen level of adventurousness. </p>
<p>We believe that this approach results in recommendations of both people and music that are more accurate, interesting and full of surprises.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

