Getting Value from Your Data; Cognitive Technology Event Warning System

Getting Value from Your Data in Hadoop

Drew Hylbert, VP of Technology Opower

Peter Schlampp, VP of Product Platfora

Your organization has implemented Hadoop because you understand it’s value. Hadoop offers a massively scalable solution to cost-effectively store large data sets and eliminate data silos. But it’s a challenge to get data in Hadoop to your business users. It requires building complex ETL processes and rigid data warehouses. In this talk Drew Hylbert, VP of Technology and Infrastructure, will give an overview of how OPower is using Hadoop and what challenges he faced in getting value from the data. Peter Schlampp, VP of Product and BD, will discuss how Platfora provides an in-memory self-service solution that provides business users access to all the data in Hadoop.

Bio:

Drew Hylbert is Opower’s Vice President of Technology and Infrastructure, overseeing IT and Systems Infrastructure and leading development of Opower's Data Infrastructure and Platform Services from the company’s San Francisco office. He was the evangelist behind the adoption of the Hadoop-based data storage infrastructure for time-series and event data, allowing Opower to scale data storage and processing infrastructure quickly and cost-effectively. Prior to Opower, Drew was Vice President of Engineering at hi5.com, a social gaming and virtual good transaction platform where he was responsible for all engineering teams with a personal focus on large-scale relevancy data infrastructure. His work there focused on the processing of billions of events daily to produce products like friend suggestions, friend filtering by interactions (friend relevancy), and interactive news feeds. Prior to hi5, Drew was a member of Yahoo’s map/reduce and data warehousing infrastructure team. Drew earned his B.S. in Computer Science from the University of Illinois Urbana-Champaign.

Peter Schlampp of Platfora is passionate about designing products that change the way users live, work, and interact with their world. He experienced first-hand the utility and complexity of big data while building products to secure enterprise networks. Peter has led Product and Marketing teams at Solera Networks, IronPort Systems, and Cisco Systems.

Cognitive Technology Event Warning System

Santosh Srinivasaiah, Booz Allen Hamilton

Data / Intelligence analysts are able to accurately identify events in any given text / data. The CTEWS (Cognitive Technology Event Warning System) will enable and assist in capturing and recording these events so as to automate the sequences surrounding an analyst. This program will integrate an EEG Recorder (Brain Waves Reader), Hadoop Ecosystem and machine learning language (WEKA) combined together to form a composite software/human-in-the-loop system capable of detecting and recording adverse events.

Note: We use a commercially available Brain wave reader to read and analyze Cognitive states of a user’s brain. The idea is to capture "Interestedness" - The state of being Interested from an analyst and translate that to machine learning language to build an CTEWS system.

Demo: There will be a demo where I will control some software programs using my brain and maybe more (Time Permitting)

Bio:

Santosh is a senior software developer for Booz Allen Hamilton, on Java technologies. His work, interest and passion has been in using BCI interfaces (Neuro-Technology) to read Cognitive brain waves and Interpret them using Java. Santosh is working on developing Algorithms that are helpful, but computers aren’t much good at detecting the unexpected and they don’t have the sort of associative memory that humans enjoy. In fact, human beings are actually very good at detecting things, and the more unusual or of interest to a person, the better.

Schedule

6:00-7:00 - Snacks and Networking

7:00-7:15 - Announcements

7:15-7:45 - Drew Hylbert and Peter Schlampp

7:45-7:50 - Break

7:50-8:20 - Santosh Srinivasaiah