<?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 for bigdata.be</title>
	<atom:link href="http://bigdata.be/comments/feed/" rel="self" type="application/rss+xml" />
	<link>http://bigdata.be</link>
	<description>Belgian community about big data, NoSQL and anything cloud</description>
	<lastBuildDate>Tue, 12 Jun 2012 19:58:19 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.5.1</generator>
	<item>
		<title>Comment on The 7th meetup or Waiting for CSI Ixelles by wim.vanleuven</title>
		<link>http://bigdata.be/2012/06/12/the-7th-meetup-or-waiting-for-csi-ixelles/#comment-123</link>
		<dc:creator>wim.vanleuven</dc:creator>
		<pubDate>Tue, 12 Jun 2012 19:58:19 +0000</pubDate>
		<guid isPermaLink="false">http://bigdata.be/?p=238#comment-123</guid>
		<description><![CDATA[Hey Lode, sorry you had to miss out on this terrific meetup. We did notice your previous request on broadcasting the meetups. We&#039;ll discuss it further down the line. As a matter of fact, let&#039;s put it on the agenda for the 8th meetup. However, we already envisaged 2 issues with your request. First of all, the logistics are a bit more elaborate that just use Google Hangout for broadcasting: camera, proper audio, etc. Second, having our meetups broadcasted would probably reinforce the effect that more and more big data geeks follow the meetups from their comfy couches. And that of course, would be counter-intuitive to the idea of having meetups in the first place. Let us know what you think!]]></description>
		<content:encoded><![CDATA[<p>Hey Lode, sorry you had to miss out on this terrific meetup. We did notice your previous request on broadcasting the meetups. We&#8217;ll discuss it further down the line. As a matter of fact, let&#8217;s put it on the agenda for the 8th meetup. However, we already envisaged 2 issues with your request. First of all, the logistics are a bit more elaborate that just use Google Hangout for broadcasting: camera, proper audio, etc. Second, having our meetups broadcasted would probably reinforce the effect that more and more big data geeks follow the meetups from their comfy couches. And that of course, would be counter-intuitive to the idea of having meetups in the first place. Let us know what you think!</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on The 7th meetup or Waiting for CSI Ixelles by André Kelpe</title>
		<link>http://bigdata.be/2012/06/12/the-7th-meetup-or-waiting-for-csi-ixelles/#comment-122</link>
		<dc:creator>André Kelpe</dc:creator>
		<pubDate>Tue, 12 Jun 2012 19:54:19 +0000</pubDate>
		<guid isPermaLink="false">http://bigdata.be/?p=238#comment-122</guid>
		<description><![CDATA[You are totally right, that it would be great to have videos of the meetups, yet it all works only out with personal initiative :-) I am not convinced that google-hangout is a good format for this as some people (including me) like to walk around while talking and not sit in front of a webcam. 

That being said, it should be easy to find a cheap video cam and record the sessions. Then of course somebody has to do the editing and upload it to youtube. That is, like bigdata.be all voluntary work, that somebody has to be willing to do. If you could find somebody to become the official video gatekeeper or even better do that yourself, I guess we always will have a video.]]></description>
		<content:encoded><![CDATA[<p>You are totally right, that it would be great to have videos of the meetups, yet it all works only out with personal initiative <img src='http://bigdata.be/wp-includes/images/smilies/icon_smile.gif' alt=':-)' class='wp-smiley' />  I am not convinced that google-hangout is a good format for this as some people (including me) like to walk around while talking and not sit in front of a webcam. </p>
<p>That being said, it should be easy to find a cheap video cam and record the sessions. Then of course somebody has to do the editing and upload it to youtube. That is, like bigdata.be all voluntary work, that somebody has to be willing to do. If you could find somebody to become the official video gatekeeper or even better do that yourself, I guess we always will have a video.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Real estate project &#8211; Minutes from kickoff by kenny</title>
		<link>http://bigdata.be/2011/11/29/real-estate-project-minutes-from-kickoff/#comment-36</link>
		<dc:creator>kenny</dc:creator>
		<pubDate>Wed, 21 Dec 2011 07:11:55 +0000</pubDate>
		<guid isPermaLink="false">http://bigdata.be/?p=206#comment-36</guid>
		<description><![CDATA[Hi Peter,
Nice to meet you and your work on immoreus.be! I had never heard about this project before, but it is indeed highly relevant to our bigdata.be project (and many other people!). Given the name of our group, we mainly intend to approach this challenge from a bigdata perspective. We have therefore started to manage our data in HBase, which enables us to continuously gather more and more heterogenous data for each house without database schema constraints.
We will only tackle the machine learning and text mining problems in a later phase of the project, yet again, we will approach this from a bigdata perspective and make use of the algorithms provided in the apache Mahout framework. 

You are most welcome to join us and discuss immoreus to our approach on of the upcoming meetups on this project! More information @ http://www.meetup.com/bigdatabe/]]></description>
		<content:encoded><![CDATA[<p>Hi Peter,<br />
Nice to meet you and your work on immoreus.be! I had never heard about this project before, but it is indeed highly relevant to our bigdata.be project (and many other people!). Given the name of our group, we mainly intend to approach this challenge from a bigdata perspective. We have therefore started to manage our data in HBase, which enables us to continuously gather more and more heterogenous data for each house without database schema constraints.<br />
We will only tackle the machine learning and text mining problems in a later phase of the project, yet again, we will approach this from a bigdata perspective and make use of the algorithms provided in the apache Mahout framework. </p>
<p>You are most welcome to join us and discuss immoreus to our approach on of the upcoming meetups on this project! More information @ <a href="http://www.meetup.com/bigdatabe/" rel="nofollow">http://www.meetup.com/bigdatabe/</a></p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Real estate project &#8211; Minutes from kickoff by Peter Loomans</title>
		<link>http://bigdata.be/2011/11/29/real-estate-project-minutes-from-kickoff/#comment-35</link>
		<dc:creator>Peter Loomans</dc:creator>
		<pubDate>Tue, 20 Dec 2011 14:47:00 +0000</pubDate>
		<guid isPermaLink="false">http://bigdata.be/?p=206#comment-35</guid>
		<description><![CDATA[Great idea!

I actually worked already on this idea for a while. Have a look at www.immoreus.be.

Based on historical real estate transactions Immoreus gives an estimate of the value of a house and also its rent value in case of an apartment. Most important driver of the value is of course the location. Therefore a lot of time and effort was spend on modeling this component accurately. You can find a high level visualization on the following page:
http://www.immoreus.be/vastgoedprijzenmap. The actual valuation algorithm produces more accurate results but due to performance reasons the map is generated with lower accuracy.

Concepts that are used:
•	Support Vector Machines
•	Neural Networks
•	Some other homebrew statistical techniques
•	Plain vanilla MySql

I could probably look into MapReduce to speed up some calculations but a large part can be done offline so currently this is not yet a bottleneck.

The best way to increase the accuracy is currently just gathering more data.]]></description>
		<content:encoded><![CDATA[<p>Great idea!</p>
<p>I actually worked already on this idea for a while. Have a look at <a href="http://www.immoreus.be" rel="nofollow">http://www.immoreus.be</a>.</p>
<p>Based on historical real estate transactions Immoreus gives an estimate of the value of a house and also its rent value in case of an apartment. Most important driver of the value is of course the location. Therefore a lot of time and effort was spend on modeling this component accurately. You can find a high level visualization on the following page:<br />
<a href="http://www.immoreus.be/vastgoedprijzenmap" rel="nofollow">http://www.immoreus.be/vastgoedprijzenmap</a>. The actual valuation algorithm produces more accurate results but due to performance reasons the map is generated with lower accuracy.</p>
<p>Concepts that are used:<br />
•	Support Vector Machines<br />
•	Neural Networks<br />
•	Some other homebrew statistical techniques<br />
•	Plain vanilla MySql</p>
<p>I could probably look into MapReduce to speed up some calculations but a large part can be done offline so currently this is not yet a bottleneck.</p>
<p>The best way to increase the accuracy is currently just gathering more data.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on One day to go &#8230; by wim.vanleuven</title>
		<link>http://bigdata.be/2011/07/04/one-day-to-go/#comment-6</link>
		<dc:creator>wim.vanleuven</dc:creator>
		<pubDate>Wed, 06 Jul 2011 19:16:49 +0000</pubDate>
		<guid isPermaLink="false">http://bigdata.be/?p=129#comment-6</guid>
		<description><![CDATA[Thanks for the valuable input, Eric. We will have to collect and curate that information somewhere!

Regarding different topics of yesterday, we probably will publish the minutes we took during the meetup. But note that we will not be creating a full transcription of the discussions.

Thanks for participating!]]></description>
		<content:encoded><![CDATA[<p>Thanks for the valuable input, Eric. We will have to collect and curate that information somewhere!</p>
<p>Regarding different topics of yesterday, we probably will publish the minutes we took during the meetup. But note that we will not be creating a full transcription of the discussions.</p>
<p>Thanks for participating!</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on One day to go &#8230; by Eric Charles</title>
		<link>http://bigdata.be/2011/07/04/one-day-to-go/#comment-5</link>
		<dc:creator>Eric Charles</dc:creator>
		<pubDate>Wed, 06 Jul 2011 08:44:27 +0000</pubDate>
		<guid isPermaLink="false">http://bigdata.be/?p=129#comment-5</guid>
		<description><![CDATA[Thx for this first meeting. Seems like BigData in BE has something to say!

My small contribution on the first part of the meeting regarding datasets sources (credit to Manning&#039;s Hadoop in Action book):
- http://aws.amazon.com/publicdatasets
- http://boston.lti.cs.cmu.edu/Data/clueweb09
- http://www.netflixprize.com/index

Unfortunately, I had to leave during the break (otherwise I should have taken a room in Brussels) and was not able to get the BBuz debrief and the other topics on the agenda. Any plan to send it or publish it?]]></description>
		<content:encoded><![CDATA[<p>Thx for this first meeting. Seems like BigData in BE has something to say!</p>
<p>My small contribution on the first part of the meeting regarding datasets sources (credit to Manning&#8217;s Hadoop in Action book):<br />
- <a href="http://aws.amazon.com/publicdatasets" rel="nofollow">http://aws.amazon.com/publicdatasets</a><br />
- <a href="http://boston.lti.cs.cmu.edu/Data/clueweb09" rel="nofollow">http://boston.lti.cs.cmu.edu/Data/clueweb09</a><br />
- <a href="http://www.netflixprize.com/index" rel="nofollow">http://www.netflixprize.com/index</a></p>
<p>Unfortunately, I had to leave during the break (otherwise I should have taken a room in Brussels) and was not able to get the BBuz debrief and the other topics on the agenda. Any plan to send it or publish it?</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on We want you! by bigdata.be &#187; Blog Archive &#187; bbuz &#8211; the day after</title>
		<link>http://bigdata.be/2011/06/01/we-want-you/#comment-4</link>
		<dc:creator>bigdata.be &#187; Blog Archive &#187; bbuz &#8211; the day after</dc:creator>
		<pubDate>Thu, 09 Jun 2011 07:11:47 +0000</pubDate>
		<guid isPermaLink="false">http://bigdata.be/?p=72#comment-4</guid>
		<description><![CDATA[[...] There were quite some bigdata.be people present at the event: Andre Kelpe, Wim Van Leuven and Steven Noels (who presented on Lily) with 2 of his colleagues at Outherthought. Of course we weren&#8217;t noticeable amongst the crowd of about 450 data geeks: we might have missed some other Belgians out there. So, if you were there or know somebody who was, please step forward and get in touch! We want you! [...]]]></description>
		<content:encoded><![CDATA[<p>[...] There were quite some bigdata.be people present at the event: Andre Kelpe, Wim Van Leuven and Steven Noels (who presented on Lily) with 2 of his colleagues at Outherthought. Of course we weren&#8217;t noticeable amongst the crowd of about 450 data geeks: we might have missed some other Belgians out there. So, if you were there or know somebody who was, please step forward and get in touch! We want you! [...]</p>
]]></content:encoded>
	</item>
</channel>
</rss>
