PMML, the Predictive Model Markup Language, has become the de-facto standard to represent not only predictive models, but also data pre- and post-processing. In so doing, it allows for the interchange of models among different tools and environments, avoiding proprietary issues and incompatibilities.
Model Building: IBM SPSS
IBM SPSS Modeler and IBM SPSS Statistics are extremely powerful data analysis and model building environments. This power is backed-up by their support of PMML. In either tool, predictive models as well as data transformations can be easily exported into PMML. IBM SPSS Statistics, for example, allows for automatic data preparation which can be exported into PMML and subsequently merged into the final PMML file for the entire solution.
View on-demand replay of the joint IBM SPSS/Zementis webcast focusing on the synergies between IBM SPSS and Zementis ADAPA (presented, May 14th, 2012).
Model Execution: ADAPA on the IBM SmartCloud
Once exported in PMML, your IBM SPSS models can be readily deployed in the Zementis ADAPA Scoring Engine, where they can be put to work immediately. To minimize total cost of ownership, model execution in ADAPA is now available as a service through the IBM SmartCloud.
View on-demand replay of the joint IBM/Zementis webcast focusing on predictive analytics deployment and execution on the IBM SmartCloud (presented, May 24th, 2012).
Review IBM developerWorks article about executing predictive solutions using ADAPA on the IBM SmartCloud.
In-database Scoring: UPPI for IBM Netezza
Predictive solutions expressed in PMML can also be put to work inside the database with the Zementis Universal PMML Plug-in (UPPI) which is now available for IBM Netezza. Since UPPI transforms your complex predictive solutions into SQL functions, these can be readily used in any query and generate instant business decisions and insights where and when you need them.