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.

Prerequisite knowledge

• 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