Data filtering for reliable decision making. Photo credit: Getty-images In this post we present our data-driven approach to design a relevant filter for ABTest result analysis… Criteo Engine consists of distinct components (bidder, recommender system, banner renderer, marketplace,...
MLconf New York 15 April, 230 fifth Avenue NY 10001. Abstract This talk, will briefly introduce the display advertising marketplace, its stakeholders and the key performance metrics. We will then present the models we have developed at Criteo...
There is a wide gap between academic machine learning and industrial data science. The goal of this workshop was to bring together researchers from academia and industry to share experiences. In particular, it was an occasion to discuss...
At Criteo, machine learning lies at the core of our business. We use machine learning for choosing when we want to display ads as well as for personalized product recommendations and for optimizing the look & feel of...
Several months ago we announced the availability of a larger version of a dataset that we released for the Kaggle click prediction challenge. We are now very pleased to report that it is currently used by an exciting Edx course about Machine Learning...
New Dataset Criteo is pleased to announce the release of a new dataset which is an extended version of our Kaggle click prediction dataset. With over 4 billion lines and over 1TB in size, this is the largest public...
We have launched a Kaggle challenge on CTR prediction 3 months ago. Large participation, close race … …and the winner will officially be announced next week! Some updates on the contest have been presented at the Paris Machine Learning Meetup....
We are committed at Criteo to scientific excellence. And one of the cornerstone of scientific progress is the reproducibility of experimental results. We thus decided to publicly release the datasets used in our forthcoming papers. And the first...
We have launched two weeks ago an exciting challenge on the Kaggle platform. We provided one week of anonymized data and the goal is very, very easy : prove that you rock in CTR prediction! I am pleased to...
