Using Data Science Techniques for Automatic Clustering of IT Infrastructure

October 2, 2014
IT departments within large organizations struggle with a common problem of infrastructure and operational management. Infrastructure components (such as storage, server, network devices, etc.) that support business critical applications generate thousands of alerts per day that report on the health of these components. Furthermore, thousands of incident tickets also get created manually. It is labor intensive and expensive to analyze all of these alerts and incidents to extract information and improve operational efficiency. In this webinar we will present a framework that was developed to automatically cluster these alerts (semi-structured text) . The framework was implemented on top of Pivotal Greenplum Database (GPDB) and draws approaches from Graph Theory and Hierarchical Clustering. It helps IT departments understand, for example, the top-20 issues that keep their support personnel busy. It can also help determine the mean-time-to-repair for a group of alerts, and more. These insights can help IT departments improve their operational efficiency. Panelist: Regunathan Radhakrishnan, Principal Data Scientist, Pivotal Hosted by: Tim Matteson, Co-Founder -- Data Science Central To learn more about Pivotal Data Science Labs, visit: http://www.pivotal.io/agile/pivotal-data-labs
Previous
Made for Each Other Microservices + PaaS
Made for Each Other Microservices + PaaS

Companies need to build better software faster to compete. But existing monolithic applications, legacy pla...

Next
Pivotal Data Science Team presents: Stuck in Traffic. Saved by Big Data!
Pivotal Data Science Team presents: Stuck in Traffic. Saved by Big Data!

As traffic volumes in cities around the world are constantly growing we are faced with the challenge to tra...

Cloud-Native Roadshow

Find your city