ALGORITHMS KEY TO EACH STAGE OF MODELING PROCESS.

Companies engaged in drug discovery, genomic research, molecular screening and other bioinformatics work, who wish to rapidly incorporate advanced data mining features into their applications can now do so by using NAG Data Mining Components as building blocks. The rigorously tested NAG Data Mining Components from the Numerical Algorithms Group are expected to significantly reduce application development schedules for project managers and developers. With the NAG Data Mining Components, there is no need to research methods, code, debug, test and document data mining routines. The savings in development cost, time, and future maintenance issues can provide project teams with a significant competitive edge.

The easy-to-integrate NAG Data Mining Components are statistical and artificial intelligence software components specifically developed for the rigors of mining massive datasets. Robust, reliable and accurate algorithms are included in the Data Mining Components for each stage of the modeling process -data preparation (case wise deletion and dummy variables generation), data transformation (principle component analysis and data scaling), and model building (decision tree analysis; K-means and hierarchical clustering; multi-layer perceptron neural networks; logistic regression; general multiple regression). Application developers can use these components in their own application designs using standard development tools.

The NAG Data Mining Components are geared to help developers select the most appropriate modeling methods quickly and easily. Some of the algorithms can be called in a "novice" mode to get results faster or in "expert" mode to provide precise control of the algorithm. Less experienced users can also get the benefit of detailed advice via hyperlinked documentation guiding them to data mining solutions most applicable to their data.

Unlike many other commercially available data mining tools, the NAG Data Mining Components are designed to be incorporated into the user's application rather than requiring the user to learn a new interface to gain access to additional techniques. Closely integrating NAG Data Mining Components allows application developers to get exactly what the users need rather than accept the available results provided by other commercially available data mining tools.

Rob Meyer, executive vice president of NAG Inc. explained that NAG Data Mining Components were developed in response to requests by various commercial companies and researchers now using data mining techniques to make better use of the vast and growing datasets that are now commonplace. "NAG's worldwide numerical experts have long been relied upon for accurate, robust and reliable algorithms that can be used as the building blocks of any application that uses math or statistical routines. With NAG's Data Mining Components, we are applying those same resources to this emerging body of analytical methods, permitting software developers to quickly and easily enhance existing or new applications with data mining techniques. The NAG Data Mining Components allow quick prototyping of customized applications by eliminating the weeks and months it often takes to develop, debug, test and maintain these methods. With NAG Data Mining Components, you can reduce project schedules, development expense, future maintenance headaches and key person dependency while using the latest methods from a trusted source.

Written in C for Windows, Linux or Solaris platforms, NAG Data Mining Components can extract data from flat files or OBDC compliant databases.

NAG is a 30-year old company dedicated to making cross-platform mathematical, statistical, data mining components and tools for developers as well as 3D visualization application development environments. It operates worldwide with hubs in Chicago (Downers Grove), UK (Oxford), and Tokyo. Today it serves over 10,000 sites worldwide in finance, engineering, and scientific research as well as commercial software firms such as PeopleSoft, IBM/Informix, Intel, and many others.

For more information, visit http://www.nag.com or call call 773-973-2077.