Why You See What You Like: Machine Learning In Modern Publishing


Machine learning systems have permeated nearly every aspect of our digital lives. We live in a time dominated by applications guiding our decisions and serving us content selected for us by a model somewhere.

What goes into building such systems at scale? We want to offer a behind-the-scenes look at how Conde Nast has led the publishing industry into the digital era by adopting a data-driven approach to content and audience intelligence.

Have you ever read an article in the New Yorker? Wired? Ever liked a post by Vogue on Twitter or Facebook? Then you’ve probably seen our machine learning systems in action.

We will talk about ML engineering and operations behind these systems at Conde Nast. How did we build an audience segmentation platform that helps advertisers serve relevant ads? How do we recommend articles for personalized newsletters? How do we determine whether a social media post is likely to go viral?

We will focus on the general design of systems that enable such cool things. Specifically, we will delve into why we chose different types of infrastructures for different projects and some of the challenges we faced when developing scalable and reliable machine learning systems.

We will focus on how we build systems that adapt well to changing data and the key components necessary for the maintainability of such systems. Additionally, we will also talk about how we structure and design the core abstractions of a system in a modular manner to enable more flexibility and faster development.

Through this talk, we want to shed light on how machine learning can empower a publishing company spread out across various geographies, genres, and brands, directly or indirectly, by improving key business metrics.

Hopefully, our learnings can help other ML engineers choose better infrastructures and designs for their systems and eliminate some common pain points.


Astha Mehta is a Machine Learning Engineer at Condé Nast, where she works on building large-scale audience segmentation, recommendation, and personalization platforms. She currently leads the effort to redesign a content recommendation framework for newsletter personalization. Astha comes with vast experience in data science with over 4 years spent on research and development of media measurement assets. She is enthusiastic about designing simple, scalable systems that enable the company to grow its machine learning capabilities.

Open Data Science




Open Data Science
One Broadway
Cambridge, MA 02142

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Consent to display content from - Youtube
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google