Predictive Model Deployment and Execution Made Easy with PMML

Developed by the Data Mining Group (DMG), an independent, vendor led committee, PMML provides an open standard for representing data mining models. In this way, models can easily be shared between different applications avoiding proprietary issues and incompatibilities. Currently, all major commercial and open source data mining tools support PMML. These include IBM/SPSS, SAS, KXEN, TIBCO, STATISTICA, Microstrategy, R, KNIME, and RapidMiner (for a list of PMML-compliant tools, see of PMML-powered tools at DMG.org).

Developed by the Data Mining Group (DMG), an independent, vendor led committee, PMML provides an open standard for representing data mining models. In this way, models can easily be shared between different applications avoiding proprietary issues and incompatibilities. Currently, all major commercial and open source data mining tools support PMML. These include IBM/SPSS, SAS, KXEN, TIBCO, STATISTICA, Microstrategy, R, KNIME, and RapidMiner (for a list of PMML-compliant tools, see of PMML-powered tools at DMG.org).

PMML is an XML-based language which follows a very intuitive structure to describe data pre- and post-processing as well as predictive algorithms. Not only does PMML represent a wide range of statistical techniques, but it can also be used to represent input data as well as the data transformations necessary to transform raw data into meaningful features.

The PMML Converter

As part of the Data Mining Group, Zementis is committed to the continual development of PMML. It is our vision for the community that users will be free to share models among many solutions, benefiting from an environment in which interoperability is truly attainable.

In this spirit, Zementis has made available a tool called the PMML Converter which converts older versions of PMML to its latest, Version 4.0. The converter is also used to validate a data mining model against the PMML specification for versions 2.0, 2.1, 3.0, 3.1, 3.2, 4.0 and 4.1. If validation is not successful, the converter gives back a file containing explanations for why the validation failed (click on the “details” button).

Before actual conversion takes place, the validation phase needs to be successful, i.e. the model file needs to conform to the PMML specification as published by the DMG (for any of the older PMML versions listed above). For known PMML issues (from a variety of sources/vendors), the PMML Converter will actually correct the model file so that it can be converted appropriately.

The PMML converter currently converts the following model elements to PMML 4.1:

• Association Rules
• Clustering Models
• Decision Trees
• General Regression Models Regression
• Naive Bayes Classifiers
• Neural Networks Regression Models
• Ruleset Models
• Scorecards
• Support Vector Machines
• Multiple Models: Ensemble, Composition, Segmentation and Chaining

It will also convert pre- and post-processing PMML elements.

The PMML Converter can be found in the Zementis PMML Tools page.

For more information on how to use the converter, please refer to the how-to guide.

The ADAPA Decision Engine

If you are using the Zementis ADAPA Decision Engine, there is no need to use the PMML Converter before uploading your models. That’s because ADAPA encapsulates the PMML Converter. By doing that, it understands PMML files generated by different vendors in all the different PMML versions. Besides syntactic validation, ADAPA also validates PMML from a semantic perspective.

And so, once a model is successfully uploaded in ADAPA, it is syntactically and semantically sound. For more details, click HERE.

You can benefit from ADAPA today by signing up for your private ADAPA instance on the Amazon Cloud or on the IBM SmartCloud. You can also sign up for the ADAPA free trial.

Start executing your models right now!