<?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: Are you more like most people? Or are you more like people who are more like you?</title>
	<atom:link href="http://thinkstream.net/2008/02/19/are-you-more-like-most-people-or-are-you-more-like-people-who-are-more-like-you/feed/" rel="self" type="application/rss+xml" />
	<link>http://thinkstream.net/2008/02/19/are-you-more-like-most-people-or-are-you-more-like-people-who-are-more-like-you/</link>
	<description>Politics and the Internet, emerging web technology, and general commentary on the way things ought to be.</description>
	<lastBuildDate>Tue, 28 Oct 2008 20:42:00 -0500</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.0.1</generator>
	<item>
		<title>By: Amaryllis</title>
		<link>http://thinkstream.net/2008/02/19/are-you-more-like-most-people-or-are-you-more-like-people-who-are-more-like-you/comment-page-1/#comment-7</link>
		<dc:creator>Amaryllis</dc:creator>
		<pubDate>Tue, 28 Oct 2008 20:42:00 +0000</pubDate>
		<guid isPermaLink="false">http://thinkstream67.wordpress.com/2008/02/19/are-you-more-like-most-people-or-are-you-more-like-people-who-are-more-like-you#comment-7</guid>
		<description>You write very well.</description>
		<content:encoded><![CDATA[<p>You write very well.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Matthew Dybwad</title>
		<link>http://thinkstream.net/2008/02/19/are-you-more-like-most-people-or-are-you-more-like-people-who-are-more-like-you/comment-page-1/#comment-6</link>
		<dc:creator>Matthew Dybwad</dc:creator>
		<pubDate>Thu, 21 Feb 2008 19:25:00 +0000</pubDate>
		<guid isPermaLink="false">http://thinkstream67.wordpress.com/2008/02/19/are-you-more-like-most-people-or-are-you-more-like-people-who-are-more-like-you#comment-6</guid>
		<description>Another interesting look at this from a story Howard sent from the Freakonomics blog at NY Times:When Your Computer Calls You a NerdIt seems not everyone is happy with the algorithm that Netflix is using.  From comments posted to that story, it seems there may be other factors being used to produce recommendations.  From  this comment on the post, it seems that &quot;Helvetica&quot; is being recommended widely because Netflix has a vested financial interest in the movie doing well since its parent company is distributing it.Another commenter goes on to explain how the algorithm doesn&#039;t represent his tastes accurately because his tastes are outside the mainstream.  He can&#039;t be pegged by a favorite actor or director in a particular film, so the recommendations don&#039;t do him any good.Perhaps because of this, Netflix is offering $1 Million dollars to anyone who can improve their algorithm.  Are better algorithms the answer?  Will advanced math ever really be able to replace the idiosyncrasies of personal taste?</description>
		<content:encoded><![CDATA[<p>Another interesting look at this from a story Howard sent from the Freakonomics blog at NY Times:When Your Computer Calls You a NerdIt seems not everyone is happy with the algorithm that Netflix is using.  From comments posted to that story, it seems there may be other factors being used to produce recommendations.  From  this comment on the post, it seems that &#8220;Helvetica&#8221; is being recommended widely because Netflix has a vested financial interest in the movie doing well since its parent company is distributing it.Another commenter goes on to explain how the algorithm doesn&#8217;t represent his tastes accurately because his tastes are outside the mainstream.  He can&#8217;t be pegged by a favorite actor or director in a particular film, so the recommendations don&#8217;t do him any good.Perhaps because of this, Netflix is offering $1 Million dollars to anyone who can improve their algorithm.  Are better algorithms the answer?  Will advanced math ever really be able to replace the idiosyncrasies of personal taste?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Matthew Dybwad</title>
		<link>http://thinkstream.net/2008/02/19/are-you-more-like-most-people-or-are-you-more-like-people-who-are-more-like-you/comment-page-1/#comment-5</link>
		<dc:creator>Matthew Dybwad</dc:creator>
		<pubDate>Tue, 19 Feb 2008 18:40:00 +0000</pubDate>
		<guid isPermaLink="false">http://thinkstream67.wordpress.com/2008/02/19/are-you-more-like-most-people-or-are-you-more-like-people-who-are-more-like-you#comment-5</guid>
		<description>Good points, Howard, thanks for leaving the first comment on my blog!I agree with your point about Amazon, at that scale they can compare my purchases with everyone else who has the same purchases and recommend those products that shake out as statistically significant.  I think though that there is value to be added to the process if users are willing to identify with other users, particularly on matters of taste as they relate to content.Initially my idea was centered on taste, but I wonder if aggregating your own interests attributes could map to decisions on other product decisions that are less subjective.  Could a person receive input on decisions about what to purchase based not only on quality and price point but also practicality and suitability observed by people in similar positions?  This could have impact from socio-economic and geographic angles and probably many more.</description>
		<content:encoded><![CDATA[<p>Good points, Howard, thanks for leaving the first comment on my blog!I agree with your point about Amazon, at that scale they can compare my purchases with everyone else who has the same purchases and recommend those products that shake out as statistically significant.  I think though that there is value to be added to the process if users are willing to identify with other users, particularly on matters of taste as they relate to content.Initially my idea was centered on taste, but I wonder if aggregating your own interests attributes could map to decisions on other product decisions that are less subjective.  Could a person receive input on decisions about what to purchase based not only on quality and price point but also practicality and suitability observed by people in similar positions?  This could have impact from socio-economic and geographic angles and probably many more.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Howard</title>
		<link>http://thinkstream.net/2008/02/19/are-you-more-like-most-people-or-are-you-more-like-people-who-are-more-like-you/comment-page-1/#comment-4</link>
		<dc:creator>Howard</dc:creator>
		<pubDate>Tue, 19 Feb 2008 16:56:00 +0000</pubDate>
		<guid isPermaLink="false">http://thinkstream67.wordpress.com/2008/02/19/are-you-more-like-most-people-or-are-you-more-like-people-who-are-more-like-you#comment-4</guid>
		<description>Matt,1)  Some hosts do have exhaustive knowledge - amazon.com.  2)  You should take a look at last.fm.  I think it does an excellent job of avoiding the elite tastemaker problem, as well as the &quot;I want to turn it on and listen without making a decision&quot; problem.  I&#039;m not sure how well last.fm would translate to video, but I&#039;m sure people are thinking about that right now.</description>
		<content:encoded><![CDATA[<p>Matt,1)  Some hosts do have exhaustive knowledge &#8211; amazon.com.  2)  You should take a look at last.fm.  I think it does an excellent job of avoiding the elite tastemaker problem, as well as the &#8220;I want to turn it on and listen without making a decision&#8221; problem.  I&#8217;m not sure how well last.fm would translate to video, but I&#8217;m sure people are thinking about that right now.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

