Data Mining For the Masses

A proposed data mining specification for J2EE-compliant application
servers has gotten approval from a Java standards board.

In a statement Thursday, the Java Community Process (JCP)
Executive Committee said it unanimously approved Java Specification Request
(JSR) 73 (also known as
Java Data Mining API — or JDMAPI), the industry’s first Java Data Mining
specification designed specifically to incorporate data mining into any
application that requires advanced analytics.

Previously, developers had to
rely on proprietary APIs and were forced to learn disparate interfaces for
each development language, such as C or Java.

The spec also includes a set of functions and algorithms
for classification, regression, association, clustering, and attribute
importance. The working group was also very satisfied with its work because
the API is designed to let beginners and experts use a common framework for
expanding the API.

“Widespread adoption of Java Data Mining will bring data mining to the
masses because developers can learn one API and embed analytics in any
application, regardless of vendor,” Jacek Myczkowski, Oracle vice president
of Data Mining Technologies and Life Sciences said in a statement.

Development of data mining is important in the enterprise in that it can
look for hidden patterns in a group of data that can be used to predict
future behavior. The technology is popular in the science and mathematical
fields but also is utilized increasingly by business intelligence and
analytics marketers trying to distill useful consumer data from Web sites.
For example, data mining software can help retail companies find customers
with common interests.

And while the spec is helpful for developers writing new Application
Programming Interfaces (API) and Web services standards, JSR-73 also
connects to other data mining standards such as the DMG’s Predictive Model
Markup Language, OMG’s Common Warehouse Metadata (CWM), and ISO’s Structured
Query Language Multimedia.

The Expert group achieved compatibility after noting that using JDMAPI
let developers expose a single, standard API that will be understood by a
wide variety of client applications and components running on the J2EE
Platform. The goal was to provide for data mining systems what JDBC
did for relational databases. A sister JSR, JSR-69 supporting
an API for OLAP, provided a common basis in the OMG CWM meta-model.

The realization of JSR-73 has been a long road. Development began in July
2000 and has been available to the public for review since October 2002. The
specification was spearheaded by Oracle but was also
championed by BEA Systems, Computer Associates, Desai, Nikhil, Fair Isaac
Corporation, Hyperion Solutions, IBM, KXEN, SAP AG, SAS Institute, SPSS,
Strategic Analytics and Sun Microsystems.

News Around the Web