Tim Shokair, Condé Nast | Databricks Data + AI Summit 2024
summary
Condé Nast runs its data stack in Databricks end to end, using feature store and MLflow, model-serving and feature-serving endpoints to deploy segmentation, subscription propensity, churn and price‑tolerance models across ~60 brands. A concrete build: a text-to-image search for the Vogue Runway app that indexes 1.2 million runway images and returns results in production — engagement data shows most sessions include a search. Plans focus on audio narration, richer content representations and better cross‑property recommendations.
AI-written summary · about
chapters (7)
- 0:00Introduction and role
- 1:04Data strategy at Condé Nast
- 4:03Using Databricks for AI
- 7:15Career pivot from physics
- 9:31The future of personalization
- 11:59Audio and accessibility
- 14:20Future goals and career advice
related talks
11mSteve Sobel, Databricks | Databricks Data + AI Summit 2023
14mTony Baer, dbinsight & Doug Henschen, Constellation Research | Databricks Data + AI Summit 2023
37mOn Building Production-Quality AI Systems
38mData science at The New York Times
13mVini Jaiswal | Databricks Data + AI Summit 2023
20mPredicting content virality to drive social traffic
01mDatabricks Customers
19mDatabricks