Predictive Model Markup Language (PMML)

PMML (Predictive Model Markup Language) - Also see predictive modeling.

PMML (Predictive Model Markup Language) is an XML-based language that enables the definition and sharing of predictive models between applications. A predictive model is a statistical model that is designed to predict the likelihood of target occurrences given established variables or factors. Increasingly, predictive models are being used in e-business applications, such as customer relationship management (CRM) systems, to forecast business-related phenomena, such as customer behavior. The PMML specifications establish a vendor-independent means of defining these models, so that problems with proprietary applications and compatibility issues can be circumvented.

The Data Mining Group (DMG), an independent vendor group whose membership includes IBM and Oracle, developed PMML as a means of simplifying processes involved in data mining. Because predictive models are created with statistical software, and then generally deployed by people using COBOL, C, or C++, working with and updating the models can be problematic. A PMML document contains definitions of analytic models and all the necessary information for deployment, so that a model can be worked with across various platforms, applications, and operating systems, independently of the software used to create them.

Related glossary terms: correlation, customer relationship analysis (CRA), data-driven decision management (DDDM), customer valuation, Digital Silhouettes, data-driven disaster, real-time analytics, Plutchik's wheel of emotions, clickstream analysis, customer segmentation

[Category=Data Management ]

Source: WhatIs.com, 01 September 2013 09:17:29, http://whatis.techtarget.com/glossary/Data-and-Data-Management