1410 Rue Stanley
Suite 606
Montreal, QC H3A 1P8

122 East 42nd Street
Suite 2005
NY, NY 10168




1410 rue Stanley 606
Montréal, QC H3A 1P8

122 East 42nd Street
Suite 2005
NY, NY 10168




Location map

Contact Us

How can we contact you?
Your submission, excluding personal information, will be analyzed for spam. By submitting this form, you accept the Mollom privacy policy.

Contact us


François-Michel L'Heureux's picture

StarCluster: Multiple node instance type support

Last week I released a new feature for the vanilla_improvements branch of StarCluster: multiple instance type support. It means that our cluster can now select the instance type to bid on depending on a configurable factor and the lowest spot market price for each type.

Want to see how it works? Head to the wiki. Want to know more about how I did it? Read further.

François Maillet's picture

Epic NHL goal celebration hack with a hue light show and real time machine learning

Now that the Stanley Cup playoffs have started and every other person you cross on the sidewalk is wearing a Montreal Canadiens jersey, I turned my attention to solving a serious machine learning problem: kicking off an Epic Goal Celebration at home whenever we score a goal. See footage below or click through to my blog to read about how I did it.


Nicolas Kruchten's picture

The Programmatic Waterfall Mystery: Solved

A recent article on AdExchanger asks “In the supposedly super-efficient world of RTB, why would publishers continue to waterfall their demand sources?”. The article goes on to say that the publisher’s justification is “Because it works” but that “Any economist could tell you that this is a bad idea”. I’m not an economist but I can still pull together enough auction theory to show that this practice isn’t necessarily a bad one.

Ivan Roubstov - Adgear's picture

How to Apply Social Ranking for Display Campaign Optimization

Today’s marketer is no stranger to SEO and social media. Yet if you ask how to optimize this data in the domain of programmatic display, you’ll probably hear crickets. And browsing the internet for answers is likely to secure information that is vague at best.

Given the abundance and variety of social and SEO data available to leverage, the absence of popular guidelines is a surprise. Social metrics are used to improve SEO, so why not apply the same rationale to the world of programmatic display?

Nicolas Kruchten's picture

Real-Time bidding optimization: a behind-the-scenes look at Datacratic's predictive API

Recently I presented Real-Time bidding optimization: a behind-the-scenes look at Datacratic's predictive API at PAPI's. PAPI' is the premier International Conference on Predictive APIs and Apps that showcases new machine learning APIs, techniques, architectures, and tools to build predictive applications. 

Most Popular Content of 2014 - Data Science, Visualizations & RTB Pacing

2014 was a great year for Datacratic. In addition to creating great technology and products, we hosted global meetups, held informative virtual events and created content to keep everyone up to date on product, technology and company news.

Just in case you missed it, here are our top 3 articles in 2014 with a pleasant surprise from the Datacratic content vault!