The Knowledge Exchange / Risk Management / Closer to real time

Closer to real time

Three high-performance options for timely results, accurate insights

SAS High-Performance Analytics delivers timely results and accurate insights on big data while optimally leveraging IT resources. There are three types of high-performance computing options to consider:

Grid computing

Grid computing enables SAS to automatically leverage a centrally managed grid infrastructure to achieve workload balancing, high availability and parallel processing.

In action: A financial services firm reduced probability of loan default calculation time from 96 hours to just four.

In-database computing

In-database computing moves relevant tasks closer to data, running computations inside the database to promote better data governance and speed time-to-results.

In action: A leading marketing solutions company’s scoring models used to take half a business day to process – now they’re scored in 60 seconds.

In-memory analytics

In-memory analytics allow analytic computations to be performed in-memory on co-located data. These computations leverage distributed processing across multiple blades for near real-time response times.

In action: A leading bank valued a complex portfolio of more than 44,000 financial instruments in less than 180 seconds.

Thornton May, a futurist and analytics thought leader, does a great job of answering the question of how high-performance analytics can help solve your risk and big data problems. Now that you have a better understanding of the types of high-performance options, watch this video Q&A with May. If you have other questions, write them in the comments or send me an email.  

*NOTE: This article was originally published in sascom Magazine Fourth Quarter 2011.

  • Facebook
  • Twitter
  • Digg
  • LinkedIn
  • email

One Trackback

  1. [...] R&D at SAS. Their presentation was developed to help analysts at the conference see how high-performance analytics can help with today’s big data [...]

Post a Comment

Your email is never published nor shared. Required fields are marked *


You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>