customer story
Creating a personalized experience with ML

Condé Nast creates new and engaging content experiences across
their brands with Databricks

INDUSTRY: Media and entertainment

SOLUTION: Personalized customer experience

TECHNICAL USE CASE: Data ingest and ETL, machine learning

Condé Nast, the publisher of iconic magazines such as Vogue, the New Yorker and Wired, uses data to reach over 1 billion people in print, online, on video, and on social media. With tremendous amounts of data to leverage, they struggled to manage infrastructure and enable data science productivity. With Databricks, cluster automation has eliminated unnecessary DevOps effort, Delta Lake has enabled them to build data pipelines that scale to 1 trillion data points per month, and data science innovation has been unlocked with a collaborative environment with MLflow to manage the entire ML lifecycle. This has allowed them to deliver personalized content across their brands to engage and retain customers.

Inability to Use Customer Data to Improve Content Experience

As a leading media publisher, Condé Nast manages over 20 brands in their portfolio. On a monthly basis, their web properties garner 100+ million visits and 800+ million page views producing a tremendous amount of data. The data team is focused on improving user engagement by using machine learning to provide personalized content recommendations and targeted ads. However, running vanilla Spark to power their data platform proved to be challenging:

  • Infrastructure complexity: Building and managing Spark clusters required lots of setup and constant maintenance, pulling teams from higher value activities.
  • Breaking down walls: Needed to find a common platform for teams to build data pipelines and advance analytics to better foster collaboration.
  • Too much data: Datasets were outgrowing existing data lake solutions.

Simplifying Data Pipelines and ML Lifecycles

Databricks provides Condé Nast with a fully managed cloud platform that simplifies operations, delivers superior performance, and enables data science innovation.

  • Interactive Workspace: Data scientists can collaborate, share, and track data and insights, fostering an environment of collaboration.
  • Delta Lake: As data sets grew in volume (over 1 trillion data points per month), Delta Lake can keep up and allow for more use cases, such as data rewrites and data merges.
  • Managed MLflow: With MLflow, Condé Nast can easily manage the entire machine learning lifecycle, from tracking experiments to monitoring production models.

Delighting Customers with Personalized Content Powered by AI

With Databricks as the foundation for their data analytics and machine learning efforts, Condé Nast’s newfound insights into their customers has transformed the way they drive engagement across their 20+ brands.

  • Improved customer engagement: With an improved data pipeline, Condé Nast can make better, faster, and more accurate content recommendations, improving the user experience.
  • Unified approach: Data engineering and data science teams are now solving problems together and collaborating to build new content products and experiences.
  • Built for scale: Datasets can no longer outgrow Condé Nast’s capacity to process and glean insights.
  • More models in production: With MLflow, Condé Nast’s data science teams can innovate their products faster. They have deployed over 1,200 models in production.
  • 60%
    Reduction in processing times due to faster ETL pipelines
  • 50%
    Reduction in IT operational costs
  • Faster
    time-to-insight to enabled them to experience a significant growth in business

Databricks has been an incredibly powerful end-to-end solution for us. It’s allowed a variety of different team members from different backgrounds to quickly get in and utilize large volumes of data to make actionable business decisions.”

– Paul Fryzel, Principal Engineer of AI Infrastructure, Condé Nast

Related Content


Technical Talk at Spark + AI Summit EU 2019