We had 3 talks at the 2019 Spark + AI Summit in San Francisco, CA.

Check ’em out!

Headaches and Breakthroughs in Building Continuous Applications

At SpotX, we have built and maintained a portfolio of Spark Streaming applications — all of which process records in the millions per minute. From pure data ingestion, to ETL, to real-time reporting, to live customer-facing products and features, continuous applications are in our DNA. Come along with us as we outline our journey from square one to present in the world of Spark Streaming. We’ll detail what we’ve learned about efficient processing and monitoring, reliability and stability, and long term support of a streaming app. Come learn from our mistakes, and leave with some handy settings and designs you can implement in your own streaming apps.

Apache Spark Listeners: A Crash Course in Fast, Easy Monitoring

The Spark Listener interface provides a fast, simple and efficient route to monitoring and observing your Spark application – and you can start using it in minutes. In this talk, we’ll introduce the Spark Listener interfaces available in core and streaming applications, and show a few ways in which they’ve changed our world for the better at SpotX. If you’re looking for a “Eureka!” moment in monitoring or tracking of your Spark apps, look no further than Spark Listeners and this talk!

Building an Enterprise Data Platform with Azure Databricks to Enable Machine Learning and Data Science at Scale at Sam’s Club

At Sams Club we have a long history of using Apache Spark and Hadoop. Projects from all parts of the company use Apache Spark, from fraud detection to product recommendations. Because of the scale of our business with billions of transactions and trillions of events it is often essential to use big data technologies. Until recently all of this work has run on several large on-premise Hadoop clusters.

As part of our transition to public cloud we needed to build out an enterprise scale data platform. Azure Databricks is a key component of this platform giving our data scientist, engineers, and business users the ability to easily work with the companies data. We will discuss our architecture considerations that lead to using multiple Databricks workspaces and external Azure blob storage.

We will also discuss how we move massive amounts of data to Azure on a daily basis with Airflow. Further we will discuss the self-service tools that we created to help users get their data to Azure and for us to manage the platform. Finally we will discuss our security considerations and how that played out in our architecture.