SAS: Predictive Analytics for Every One. Yes, Every One

October 19, 2015

Forget your university statistics course. Ignore the thrill of secondary school calculus. A new world has arrived. The terraformer is SAS, the statistics outfit everyone knows and loves.

I read “SAP Predictive Analytics Software Overview,” and was delighted to learn that I can now have on my desktop (sorry, mobile device users):

  • Perform data analyses, including time series forecasting, outlier detection, trend analysis, classification analysis, segmentation analysis and affinity analysis.
  • Create visualizations and analyze data through the use of scatter matrix charts, parallel coordinates, cluster charts and decision trees.
  • Use the R open source language for statistical analysis.
  • Perform in-memory data mining for large-volume data analysis.

What, you may ask, is a user to do if the underpinnings of these operations are not understood?

My hunch is that for the ease of use and point and click functions of tried and true SAS plus KXEN technology is that you may find yourself in need of a specialist.

Knowledge of SAS conventions, R, and possibly third party libraries or Hadoop may come in handy.

I am delighted that SAS, founded in 1976 is delivering innovations. Unfortunately to make predictive analytics deliver fresh bread in an optimized way will require a grasp of statistical procedures, the ability to validate input data sets, and manipulate the options presented.

In short, statistics and math skills coupled with the fundamentals of data analysis should do nicely to help you get the most from this new bundle from SAS. No word on pricing.

Stephen E Arnold, October 19, 2015

Comments

Comments are closed.

  • Archives

  • Recent Posts

  • Meta