Fault Tolerant Streaming + Spark & Cassandra + Operationalise Machine Learning

Topic 1: Fault Tolerant Streaming

Presenter: Suresh from Macquarie & Andy from Servian

Suresh and Andy will share their experience in designing a streaming application using Spark Streaming. Achieving cross data center fault tolerance and exactly once processing across different physical clusters.

Topic 2: Spark on Cassandra

Presenter: Alex from Datastax

Alex will share his experience with Spark and Cassandra

Alex has been working with Cassandra since it was first open sourced by Facebook in 2009 and has extensive background in Java, C#, Python development for many years. Alex has worked as a developer, senior developer, application architect and technical lead on some of the largest sites in Australia in the Media, Banking and Utilities industries across both open source and proprietary software stacks in mixed Windows/Linux environments. Scaling is his passion and obsession, and started early on playing with Tokyo Cabinet, Voldermort, hBase, Hypertable, before getting more heavily involved with Cassandra. More recently Alex has been working on the Titan Graph Database and its integration with Cassandra.

Alex has been with Datastax Australia since June 2014, and yes his photo is an attempt at Derke Zoolander’s blue steel look

http://photos1.meetupstatic.com/photos/event/c/8/8/1/600_449631329.jpeg

Topic 3: Operationalising Spark Machine Learning

Presenter: Alasdair from Servian

Our third topic will be lessons learned from deploying Spark machine learning system into production. Alasdair will share with us on the challenges they have faced during the project and how they managed to work through them. The team crunched through hundreds of terabytes of data to develop predictive models based on user behavior utilizing Spark.