Spark+AI Conference is in San Francisco June 4-6. It’s the preeminent conference covering all things Spark. Since 2013 the conference has helped developers learn and explore the possibilities of delivering modern data-driven applications at scale. The overarching theme of this years show is the unification of data and AI. New applications that include AI require massive amounts of constantly changing data, and Apache Spark is at the center of this data processing opportunity.
Sessions of particular interest include Spark Streaming case studies along with operationalizing Spark for production:
Tathagata Das will discuss different stateful operations in Structured Streaming, how state data is stored in a distributed, fault-tolerant manner using State Stores. Tues, June 5 @ 11am
David Crespi and Jared Piedt will be talking about taking your machine learning models to production. Tues, June 5 @ 11:40am
Nikhil Simha and Varant Zanoyan will talk about Zipline, Airbnb’s data management platform for ML. The purpose of the platform is to reduce the time collecting and writing transformations for ML tasks, claiming a month to days improvement. Tues, June 5 @ 12:20pm
Nitin Sharma and Elliot Chow will talk about how Netflix leverages real-time data for model training to deliver the right personalized video for users. Tues, June 5 @ 4:20pm
Ravikanth Durgavajhala will talk about the new Intel Optane SSD with Intel Memory Drive Technology to address memory limitations for large scale processing deployments. Wed, June 6 @ 11am
The Real-Time Database for Spark
SingleStore has been working with Apache Spark since 2015 by delivering scalable ingestion, storage, and analysis of data for real-time insights. Our 79-page Spark Connector Guide covers how to design, build, and deploy Spark applications using the SingleStore Spark Connector. You’ll find code samples to help you get started and performance recommendations for your production-ready Apache Spark and SingleStore implementations.
Download the SingleStore Spark Connector Guide.