<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	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:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Recoset: Machine Learning and Predictive Modeling</title>
	<atom:link href="http://www.recoset.com/content/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.recoset.com/content</link>
	<description>Real time Data and Advertising Technology</description>
	<lastBuildDate>Thu, 19 Apr 2012 15:37:47 +0000</lastBuildDate>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.1</generator>
		<item>
		<title>Peeking Into the Black Box, Part 2: Algorithm Meets World</title>
		<link>http://www.recoset.com/content/2011/12/peeking-into-the-black-box-part-2-algorithm-meets-world/</link>
		<comments>http://www.recoset.com/content/2011/12/peeking-into-the-black-box-part-2-algorithm-meets-world/#comments</comments>
		<pubDate>Thu, 22 Dec 2011 20:30:50 +0000</pubDate>
		<dc:creator>Nicolas Kruchten</dc:creator>
				<category><![CDATA[Technology]]></category>
		<category><![CDATA[algorithm]]></category>
		<category><![CDATA[black box]]></category>
		<category><![CDATA[economics]]></category>
		<category><![CDATA[pacing]]></category>
		<category><![CDATA[price floors]]></category>
		<category><![CDATA[profit]]></category>
		<category><![CDATA[real-time bidding]]></category>
		<category><![CDATA[recoset]]></category>
		<category><![CDATA[rtb]]></category>
		<category><![CDATA[surplus]]></category>

		<guid isPermaLink="false">http://www2.recoset.com/content/?p=255</guid>
		<description><![CDATA[In Part 1 of this series, I claimed that Recoset’s RTB algorithm is able to take advantage of other bidders’ sub-optimal behaviour and navigate around publisher price floor in order to achieve advertiser goals. I then described the algorithm, which applies what &#8230; <a href="http://www.recoset.com/content/2011/12/peeking-into-the-black-box-part-2-algorithm-meets-world/"><span class="meta-nav">&#62;&#62;</span> Read More</a>]]></description>
		<wfw:commentRss>http://www.recoset.com/content/2011/12/peeking-into-the-black-box-part-2-algorithm-meets-world/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Peeking Into the Black Box, Part 1: Recoset’s RTB Algorithms</title>
		<link>http://www.recoset.com/content/2011/12/peeking-into-the-black-box-part-1-recosets-rtb-algorithms/</link>
		<comments>http://www.recoset.com/content/2011/12/peeking-into-the-black-box-part-1-recosets-rtb-algorithms/#comments</comments>
		<pubDate>Thu, 22 Dec 2011 19:31:01 +0000</pubDate>
		<dc:creator>Nicolas Kruchten</dc:creator>
				<category><![CDATA[Technology]]></category>
		<category><![CDATA[algorithm]]></category>
		<category><![CDATA[black box]]></category>
		<category><![CDATA[economics]]></category>
		<category><![CDATA[pacing]]></category>
		<category><![CDATA[real-time bidding]]></category>
		<category><![CDATA[recoset]]></category>
		<category><![CDATA[rtb]]></category>
		<category><![CDATA[surplus]]></category>

		<guid isPermaLink="false">http://www2.recoset.com/content/?p=257</guid>
		<description><![CDATA[This article is about the statistical and economic theory that underlies Recoset’s real-time bidding strategies, as a follow-up to my previous article on how we apply control theory to pace our spending, which I’m grandfathering in as “Part 0” of this short &#8230; <a href="http://www.recoset.com/content/2011/12/peeking-into-the-black-box-part-1-recosets-rtb-algorithms/"><span class="meta-nav">&#62;&#62;</span> Read More</a>]]></description>
		<wfw:commentRss>http://www.recoset.com/content/2011/12/peeking-into-the-black-box-part-1-recosets-rtb-algorithms/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Real Time Bidding, Characterized</title>
		<link>http://www.recoset.com/content/2011/09/real-time-bidding-characterized/</link>
		<comments>http://www.recoset.com/content/2011/09/real-time-bidding-characterized/#comments</comments>
		<pubDate>Thu, 08 Sep 2011 18:30:36 +0000</pubDate>
		<dc:creator>Nicolas Kruchten</dc:creator>
				<category><![CDATA[Technology]]></category>
		<category><![CDATA[auction]]></category>
		<category><![CDATA[real-time bidding]]></category>
		<category><![CDATA[recoset]]></category>
		<category><![CDATA[rtb]]></category>

		<guid isPermaLink="false">http://www2.recoset.com/content/?p=253</guid>
		<description><![CDATA[There doesn&#8217;t appear to be a good Wikipedia entry for RTB for me to link at the moment, when I want to blog about it so I&#8217;ll draft my own explanation here. (Edit: there is an entry now, but I like &#8230; <a href="http://www.recoset.com/content/2011/09/real-time-bidding-characterized/"><span class="meta-nav">&#62;&#62;</span> Read More</a>]]></description>
		<wfw:commentRss>http://www.recoset.com/content/2011/09/real-time-bidding-characterized/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>RTB Pacing: is everyone doing it wrong?</title>
		<link>http://www.recoset.com/content/2011/09/rtb-pacing-is-everyone-doing-it-wrong/</link>
		<comments>http://www.recoset.com/content/2011/09/rtb-pacing-is-everyone-doing-it-wrong/#comments</comments>
		<pubDate>Thu, 08 Sep 2011 18:25:30 +0000</pubDate>
		<dc:creator>Nicolas Kruchten</dc:creator>
				<category><![CDATA[Technology]]></category>
		<category><![CDATA[arbitrage]]></category>
		<category><![CDATA[budget]]></category>
		<category><![CDATA[campaign]]></category>
		<category><![CDATA[control]]></category>
		<category><![CDATA[pacing]]></category>
		<category><![CDATA[real-time bidding]]></category>
		<category><![CDATA[recoset]]></category>
		<category><![CDATA[rtb]]></category>

		<guid isPermaLink="false">http://www2.recoset.com/content/?p=243</guid>
		<description><![CDATA[&#160; I&#8217;ve written some follow-up posts to this one, as a series called Peeking into the Black Box, so I&#8217;m grandfathering this post in as &#8220;Part 0&#8243; of the series. I read an interesting post on the AppNexus tech blog about their campaign &#8230; <a href="http://www.recoset.com/content/2011/09/rtb-pacing-is-everyone-doing-it-wrong/"><span class="meta-nav">&#62;&#62;</span> Read More</a>]]></description>
		<wfw:commentRss>http://www.recoset.com/content/2011/09/rtb-pacing-is-everyone-doing-it-wrong/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Using make to Orchestrate Machine Learning Tasks</title>
		<link>http://www.recoset.com/content/2011/07/using-make-to-orchestrate-machine-learning-tasks/</link>
		<comments>http://www.recoset.com/content/2011/07/using-make-to-orchestrate-machine-learning-tasks/#comments</comments>
		<pubDate>Tue, 26 Jul 2011 18:30:22 +0000</pubDate>
		<dc:creator>Nicolas Kruchten</dc:creator>
				<category><![CDATA[Technology]]></category>
		<category><![CDATA[gnu make]]></category>
		<category><![CDATA[machine learning]]></category>
		<category><![CDATA[make]]></category>
		<category><![CDATA[models]]></category>
		<category><![CDATA[parallelization]]></category>
		<category><![CDATA[recoset]]></category>
		<category><![CDATA[rtb]]></category>
		<category><![CDATA[testing]]></category>
		<category><![CDATA[training]]></category>

		<guid isPermaLink="false">http://www2.recoset.com/content/?p=251</guid>
		<description><![CDATA[One of the things we do at Recoset is to use machine learning algorithms to optimize real-time bidding (RTB) policies for online display advertising. This means we train software models to predict, for example, the cost and the value of showing a given ad impression, &#8230; <a href="http://www.recoset.com/content/2011/07/using-make-to-orchestrate-machine-learning-tasks/"><span class="meta-nav">&#62;&#62;</span> Read More</a>]]></description>
		<wfw:commentRss>http://www.recoset.com/content/2011/07/using-make-to-orchestrate-machine-learning-tasks/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Recoset&#8217;s Dataviz System</title>
		<link>http://www.recoset.com/content/2011/07/recosets-dataviz-system/</link>
		<comments>http://www.recoset.com/content/2011/07/recosets-dataviz-system/#comments</comments>
		<pubDate>Thu, 07 Jul 2011 18:30:04 +0000</pubDate>
		<dc:creator>Nicolas Kruchten</dc:creator>
				<category><![CDATA[Technology]]></category>
		<category><![CDATA[coffeescript]]></category>
		<category><![CDATA[dataviz]]></category>
		<category><![CDATA[protovis]]></category>
		<category><![CDATA[recoset]]></category>
		<category><![CDATA[visualization]]></category>

		<guid isPermaLink="false">http://www2.recoset.com/content/?p=249</guid>
		<description><![CDATA[At Recoset, working with data often means data visualization (or dataviz): making pretty pictures with data. This is usually more like making fully machine-generated images than carefully laying out &#8220;infographics&#8221; of the Information Is Beautiful school but I find they usually &#8230; <a href="http://www.recoset.com/content/2011/07/recosets-dataviz-system/"><span class="meta-nav">&#62;&#62;</span> Read More</a>]]></description>
		<wfw:commentRss>http://www.recoset.com/content/2011/07/recosets-dataviz-system/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Statsd, Graphite and Nagios</title>
		<link>http://www.recoset.com/content/2011/05/statsd-graphite-and-nagios/</link>
		<comments>http://www.recoset.com/content/2011/05/statsd-graphite-and-nagios/#comments</comments>
		<pubDate>Sun, 01 May 2011 18:23:51 +0000</pubDate>
		<dc:creator>Nicolas Kruchten</dc:creator>
				<category><![CDATA[Technology]]></category>
		<category><![CDATA[alarming]]></category>
		<category><![CDATA[dashboard]]></category>
		<category><![CDATA[devops]]></category>
		<category><![CDATA[graphite]]></category>
		<category><![CDATA[monitoring]]></category>
		<category><![CDATA[nagios]]></category>
		<category><![CDATA[open source]]></category>
		<category><![CDATA[opsview]]></category>
		<category><![CDATA[recoset]]></category>
		<category><![CDATA[software]]></category>
		<category><![CDATA[statsd]]></category>

		<guid isPermaLink="false">http://www2.recoset.com/content/?p=241</guid>
		<description><![CDATA[At Recoset we tend to worship, like Etsy (and AppNexus!), at the Church of Graphs. We&#8217;ve even started using Statsd, the system they&#8217;ve released to collect stats and relay them to Carbon for display in Graphite. And by display, I mean display on a dashboard visible &#8230; <a href="http://www.recoset.com/content/2011/05/statsd-graphite-and-nagios/"><span class="meta-nav">&#62;&#62;</span> Read More</a>]]></description>
		<wfw:commentRss>http://www.recoset.com/content/2011/05/statsd-graphite-and-nagios/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Efficient log processing</title>
		<link>http://www.recoset.com/content/2011/02/efficient-log-processing/</link>
		<comments>http://www.recoset.com/content/2011/02/efficient-log-processing/#comments</comments>
		<pubDate>Wed, 02 Feb 2011 17:38:24 +0000</pubDate>
		<dc:creator>François Maillet</dc:creator>
				<category><![CDATA[Technology]]></category>

		<guid isPermaLink="false">http://recoset.com/content/?p=414</guid>
		<description><![CDATA[I&#8217;ve recently learned a couple of neat tricks to process large amounts of text files more efficiently. Our use-case is efficiently going through tens of gigabytes of logs to extract specific lines and do some operation on them. Here are &#8230; <a href="http://www.recoset.com/content/2011/02/efficient-log-processing/"><span class="meta-nav">&#62;&#62;</span> Read More</a>]]></description>
		<wfw:commentRss>http://www.recoset.com/content/2011/02/efficient-log-processing/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
	</channel>
</rss>

