Building a Predictive Engine using SMACK (Spark, Mesos, Akka, Cassandra, Kafka)

Presented by

Natalino Busa, Enterprise Data Architect, ING

About this talk

This webinar will provide a blueprint for a predictive system using a number of bespoken open-source high available, resilient and distributed technologies: Spark, Mesos, Akka, Cassandra, Kafka, which go together as the "SMACK" stack. After briefly highlighting the characteristics of each component, we will move on connecting the part in order to build a predictive system: a machine learning module, an event processing scoring module , and a data store implemented using Spark, Akka, and Cassandra, respectively. In this webinar you will learn about the SMACK stack, as well as how to: -Determine when to use batch, microbatch and event data processing -Deploy Kafka to publish and consume events -Compute fast/big data streams using Spark, and Akka -Deploy Cassandra to persist events as well as machine learning models

Related topics:

More from this channel

Upcoming talks (3)
On-demand talks (588)
Subscribers (87930)
Data is the foundation of any organization and therefore, it is paramount that it is managed and maintained as a valuable resource. Subscribe to this channel to learn best practices and emerging trends in a variety of topics including data governance, analysis, quality management, warehousing, business intelligence, ERP, CRM, big data and more.