We now have 80% of data living in the messy horror world of proprietary
formats. If those 80% are taken over by XML, that's a big step forward.
—Alexander Jerusalem on the XML Developers mailing list
Extensible Markup Language (XML) is becoming the ubiquitous
choice for data representation in a machine-readable format and for
data exchange [W3CXML 2006]. An XML Schema provides mech-
anisms to define and describe the structure, content, and to some
extent semantics of XML documents [W3CXML-SCHEMA 2006].
In Java Data Mining (JDM), we defined an XML Schema for JDM
objects to complement the Java application programming interface
(API) and provide a standards-based data model. JDM XML Schema
definitions supported multiple uses, such as interchanging data
mining objects among data mining engines (DMEs), defining Web
services, storing data mining objects as XML documents, and inte-
grating JDM implementations with non-Java applications. Readers
of this chapter are expected to be familiar with XML and XML
Schema concepts [Ray 2003].
This chapter provides an overview of the JDM Schema, the
structure of JDM-compliant XML documents, JDM Schema complex
types, use cases for XML Schema, and lastly, how the JDM Schema
complements the Predictive Model Markup Language [DMG-PMML