Apache Big Data Europe 2016

As modern enterprises migrate to microservice-centric cloud architecture, it has become imperative to build a new data analysis framework to handle äóñ often in real time - the event-based data these services produce. For this presentation, we will demonstrate how to leverage multiple open source projects to build a robust framework quickly and cheaply that can scale with an organization as it grows and inexorably generates more and more data.

They will cover a tangible, real-world, implementation that includes Apache technologies such as Kafka, Mesos, and Spark, as well as open-source PrestoDB (Facebook).



The speakers will discuss lessons learnt during and after the build, as well as

some specific use-cases for how this approach brought about otherwise-unattainable actionable business insights and results, including hardware failure prediction and capacity planning.