Contact Sales: (619) 330-0780

Peer Reviewed

KDD 2013 – The R pmmlTransformations Package

This paper describes another R package that supports PMML, the pmmlTransformations package. The pmmlTransformations package works in tandem with the pmml package to provide a PMML representation of the model describing not just the modeling technique itself but also the data pre-processing steps, which provide the user the capability to manipulate data in different ways prior to modeling.

The R Journal and PMML

This paper describes the pmml Package, which is primarily responsible for exporting PMML, the Predictive Model Markup Language, from R model objects. Although published in The R Journal in 2009, it is still relevant today since the basis of the package is still the same, even though the breadth and depth of PMML support in R has been extended substantially in the last few years.

FICO PMML ADAPA peer reviewed KDD 2011 – Scorecard Element in PMML

In this paper, jointly written by FICO and Zementis, we describe the dedicated Scorecard element introduced in the 4.1 specification of the PMML (Predictive Model Markup Language) standard, including the various design and computational options available for returning reason codes alongside each computed score. The paper is intended to help both producers and consumers of scorecards as PMML documents.

EMC PMML ADAPA peer reviewed KDD 2011 – In-Database Predictions using PMML

In this paper, jointly written by Pivotal/Greenplum and Zementis, we describe how PMML, the Predictive Model Markup Language, enables embedding advanced predictive models directly into the database or the data warehouse, along side the actual data to be scored. More importantly, we shows how one can easily take advantage of highly parallel database architectures to efficiently derive predictions from very large volumes of data.

PMML Converter ADAPA peer reviewed KDD 2011 – PMML Converter and Transformations Generator

This paper describes the capabilities associated with the “PMML Converter” which is part of all Zementis products. The converter is responsible for making sure ADAPA and UPPI can consume any version of PMML, while automatically converting them into PMML 4.1. This paper also describes the capabilities associated with an interactive PMML-based application, the “Transformations Generator” which provides a graphical interface for the development and expression of data pre-processing steps in PMML.

KDD 2011 – PMML Pre-processing in KNIME

In this paper, jointly written by KNIME and Zementis, we describe the PMML extensions for the modular open source data analytics platform KNIME adding pre-processing support and the ability to edit existing PMML code. We also shows how the PMML model representation in KNIME can be used within meta learning schemes such as boosting and bagging.

KDD PMML ADAPA peer reviewed SiGKDD Explorations 2009 – Focus on Interoperability

In this article, we highlight the use of the PMML (Predictive Model Markup Language) standard, which allows for predictive models to be easily exchanged between analytic applications. We also focus on cloud computing and Software as a Service and use the Zementis ADAPA Scoring Engine to illustrate how the benefits of open-standards and cloud computing can be combined.

KDD 2009 – Panel on PMML and Cloud Computing

In this article, we highlight the use of the PMML (Predictive Model Markup Language) standard, which allows for predictive models to be easily exchanged between analytic applications. We also focus on cloud computing and Software as a Service and use the Zementis ADAPA Scoring Engine to illustrate how the benefits of open-standards and cloud computing can be combined.

Copyright © 2017 Zementis / Software AG. All Rights Reserved.