SAP HANA SPS 12 was released yesterday 11th May 2016. If you want to delve deeper and see working examples of what’s new for predictive in SPS 12 then this blog can serve as your starting point.
Time series analysis is a major focus area in this release with Auto-ARIMA being the new algorithm on the block.
Auto-ARIMA expands the existing ARIMA capabilities of the Predictive Analysis Library (PAL) by automatically identifying the orders of an ARIMA (Seasonal-ARIMA-X) model according to information criterion such as AICC, AIC, and BIC. The orders can be represented as (p,d,q) (P,D,Q)m, where m is the seasonal period.
Auto-ARIMA is also available in the Application Functional Modeler (AFM) enabling WYSIWYG application development without the requirement to code in SQL Script.
Many additional enhancements have been made to other time series algorithms, including addition of custom confidence limits for singe, double, and triple exponential smoothing and new options for self organizing maps such as batch support.
Here are links to tutorials covering enhancements to the Application Function Modeler (AFM) for predictive:
Here are links to the new and enhanced SAP HANA predictive analysis library (PAL) algorithms:
Here’s the full playlist for what’s new: What’s New for Predictive SPS 12
Finally, if you’re interested to learn about other stuff that’s new in SPS 12 check out the following playlist: SAP HANA SPS 12 – What’s New