Serverless and Open-Source Machine Learning at Sling Media (Cloud Next '19)

Join us to learn about Sling’s incremental adoption strategy of serverless GCP technologies to enable data scientists and engineers to deliver business value quickly. As one example, we will walk through our journey of (1) using deep learning techniques to better predict churn, (2) developing a traditional pipeline to serve the model, and (3) enhancing the pipeline to be serverless and scalable using open-source technologies and managed GCP services. We will share best practices and lessons learned deploying Beam, tf.transform, and TensorFlow on Cloud Dataflow and Cloud Machine Learning Engine.

Build with Cloud →

Watch more:
Next ’19 ML & AI Sessions here →
Next ‘19 All Sessions playlist →

Subscribe to the GCP Channel →

Speaker(s): Austin Bennett, Salma Riazi

Session ID: MLAI207
product:BigQuery,Kubernetes Engine,AI,TensorFlow;

Duration: 36:30
Publisher: Google Cloud
You can watch this video also at the source.