Software

The ADAPA� scoring engine by Zementis readied for the latest version of the Predictive Model Markup Language (PMML), version 4.0.

PMML is the de facto standard to represent data mining models. Originally proposed and now expanded by the Data Mining Group (DMG), PMML allows for true interoperability, offering a now mature standard for predictive models for moving them seamlessly between platforms.

Alex Guazzelli, Vice President of Analytics at Zementis, says: "This release announcement of PMML 4.0 attests to the commitment of the leading data mining vendors to represent their solutions through a single language, a language that can be understood by all. PMML allows for distinct platform use through all the different phases of modeling, allowing the users to choose the exact set of tools that adheres to their needs."

Zementis, together with SPSS, SAS, IBM, Open Data Group, Salford Systems, Microstrategy and the other contributing members of the DMG, is proud to be part of the making of PMML. In anticipation of the introduction of PMML 4.0, the ADAPA� scoring engine is able to score all the new pre-processing capabilities expressed in the new version.

The new 4.0 release allows for data manipulation using Boolean operators and IF-THEN-ELSE logic that provides capacity for a host of new feature detectors represented in PMML. 4.0 expands the list of modeling techniques supported by the standard including Time Series Models and Cox Regression Models, as well as a completely new element for model explanation and visualization. The Zementis ADAPA� scoring engine consumes PMML models and executes them in real-time. Available as a SaaS service through Amazon, ADAPA� is the most versatile and innovative deployment platform in the market today.

For more information please visit www.zementis.com.