Big Data: Hadoop and Beyond

(Click for PDF Slides)

For over five years, the term “Big Data” has been preeminent in the technical psyche. Many believe that “Big Data” is a marketing term and they are correct. But the term expresses a very real set of problems and, fortunately, a set of solutions as well. The challenge is to efficiently create cost-effective storage and leverage the computational power needed to make use of the poly-structured, high volume, and many times, high-velocity data that is called “Big Data.” Big data is useless, however, unless it can be transformed into consumable data that then must yield beneficial information for mission-critical or revenue-generating endeavors. The solution can be found in Hadoop and beyond.

This presentation will provide an overview of open-source big data frameworks that are currently available and a quick synopsis of where they might be applicable in your domain. The presentation will also serve as a kick-off for a series of detailed talks each focused on a specific component of a big data framework distribution, such as the Hadoop Ecosystem (from the Apache Software Foundation) and the rapidly evolving set of capabilities known as the Berkeley Data Analytics Stack (from AMPLAB).