From the announcement:
“As a standard, PMML provides the glue to unify data science and operational IT. With one common process and standard, PMML is the missing piece for Big Data initiatives to enable rapid deployment of data mining models. Broad vendor support and rapid customer adoption demonstrates that PMML delivers on its promise to reduce cost, complexity and risk of predictive analytics,” says Alex Guazzelli, Vice President of Analytics, Zementis. “You can not build and deploy predictive models over big data without using multiple models and no one should build multiple models without PMML,” says Bob Grossman, Founder and Partner at Open Data Group.
Some of the elements that are new to PMML v4.2 include:
- Improved support for post-processing, model types, and model elements
- A completely new element for text mining
- Scorecards now introduce the ability to compute points based on expressions
- New built-in functions, including “matches” and “replace” for the use of regular expressions
Hmmm, do you think they meant before 4.2 they didn’t have “matches” and “replace?” (I checked, they didn’t.)
However, kudos on the presentation of their schema, both current and prior versions.
More XML schemas had such documentation/presentation.
I first saw this at: The Data Mining Group releases PMML v4.2 Predictive Modeling Standard.