An Exploration of 3 Very Different ML Solutions Running on Accumulo

Back to Schedule

Slides

Video

Use Case

Abstract

Are your customers looking to build diverse machine learning (ML) solutions on Accumulo? In this talk, we walk through three production ML use cases that require users to interact with Accumulo in very different ways - Supply Chain Risk, Cyber Monitoring, and Forensic Document Search. We discuss the surprising result that we are able to support all of these use cases using the a common set of Accumulo tables.

Speakers

Donald Miner
Founding Partner, Miner & Kasch

Donald Miner is founder of the data science firm Miner & Kasch and specializes in large-scale data analysis enterprise architecture and applying machine learning to real-world problems. Donald is author of the O’Reilly book "MapReduce Design Patterns", and the O’Reilly reports “Hadoop with Python” and “What You Need To Know About Hadoop". He has architected and implemented dozens of mission-critical and large-scale data analysis systems within the U.S. Government and Fortune 500 companies. He has applied machine learning techniques to analyze data across several verticals, including financial, retail, telecommunications, healthcare, government intelligence, and entertainment. His PhD is from the University of Maryland, Baltimore County, where he focused on machine learning and multi-agent systems. He lives in Maryland with his wife and three young sons.

Gadalia O'Bryan
Vice President of Global Services, Koverse Inc.

Gadalia has spent her career delivering robust, repeatable software solutions with real business and mission value. She enjoys partnering with customers to rapidly move forward and see a return on investment from their big data implementations.

Gadalia worked for the National Security Agency (NSA) for nearly a decade before leaving the public sector to join Koverse. At the NSA, Gadalia built production big data solutions that are referenced by programs throughout the U.S. Department of Defense and Intelligence Community. She also led large-scale security evaluations of cryptographic algorithms and information security systems, including both commercial and government applications.

Gadalia holds a Bachelor of Arts (BA) degree in Mathematics from the University of Colorado at Boulder, where she published work in the journal Numerical Algorithms. She holds a Master of Arts (MA) degree in Mathematics from UCLA, specializing in Algebraic Topology.

Aaron Cordova
CTO, Koverse Inc.

Aaron has built multiple, large-scale, big data systems that are used by the intelligence, defense, finance and healthcare industries. Aaron is the CTO and co-founded of Koverse Inc. Prior to that, Aaron was a researcher for the National Security Agency (NSA) where he founded the Apache Accumulo project, a scalable and secure data store. He is the author of the O’Reilly book, Accumulo: Application Development, Table Design, and Best Practices.