|
Alex Guazzelli answers:
PMML (Predictive Model Markup Language) is the de facto standard to represent data mining models. PMML allows for different data mining packages to talk the same language. In this way, a model can be easily moved around among different applications. For example, it may be developed in one system and deployed on another one. PMML was developed by the Data Mining Group (DMG), a consortium of companies devoted to data mining standards. The latest version of PMML, version 4.0, was released by the DMG in June 2009.
What kind of models are supported by PMML?
PMML defines specific elements for several predictive techniques, including neural networks, decision trees, and clustering models (among others). New techniques just recently supported are time-series and Cox regression models. To review all the elements supported by PMML, take a look at the language specification at the DMG website.
Can PMML represent data pre- and post-processing?
PMML has several built-in functions, such as IF-THEN-ELSE and arithmetic functions, that allow for extensive data manipulation. It also defines specific elements for the most common pre-processing tasks such as normalization, discretization, and value mapping. To review all the pre-processing capabilities PMML has to offer, refer to the PMML pre-processing primer.
Where can I read more about PMML?
| 