Personalizing the infinite jukebox: ML and the TensorFlow ecosystem at Spotify
Who is this presentation for?
- Engineering managers, ML engineers, and data scientists
When Spotify launched in 2008, the lucky first launch countries rejoiced at the prospect of an almost infinite jukebox at their fingertips. In the 10+ years that followed, the product evolved quite a bit from something that required you to know exactly what you wanted to listen to before you listened to the product today that offers countless recommendations and a personalized experience. It’s no surprise that ML has had a prominent role in that evolution.
Josh Baer and Keshi Dai explain how Spotify applied ML to personalize its product and discuss the historical challenges of bringing ML products to market. You’ll learn how Spotify uses TensorFlow and, especially, the TFX family of products as a “paved” workflow and how this has improved the ability for product teams to leverage ML in their work. You’ll also examine the current state of the ML platform at Spotify and the open challenges the company faces.
- A basic understanding of the ML workflow and the challenges that engineers face in productionizing ML in the industry
What you'll learn
- Understand the usage of Tensorflow Extended (tf.Transform, TF Data Validation, TF Model Analysis, tf.Examples, etc.) in the enterprise and how ML works at Spotify
Josh Baer is the machine learning platform lead at Spotify, building out the tools, processing, and infrastructure for robust ML experiences; enabling teams to leverage ML and AI sustainably in their products, research, and services; and providing a cohesive experience. Previously, Josh led the Hadoop and stream processing teams.
Keshi Dai is a machine learning engineer at Spotify, working to build out ML infrastructure that supports hundreds of engineers and the growth of ML in products at Spotify. Previously, Keshi worked on the other side of ML as one of the engineers building out recommendation products at Spotify. He knows firsthand the challenges presented when productionizing ML and the benefit in using standard infrastructure in many parts of the workflow.
Leave a Comment or Question
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
For conference registration information and customer service
For more information on community discounts and trade opportunities with O’Reilly conferences
For information on exhibiting or sponsoring a conference
For media/analyst press inquires