NAG Data Mining Components


NAG’s Data Mining Components are a collection of callable components designed to help developers build fast, accurate, and robust applications for predictive analytics. You select the components you need for problem solving and readily integrate these components into your existing applications.

Data Mining Components offer routines for data cleaning (including imputation and outlier detection), data transformations (scaling, principal component analysis), clustering, classification, regression models and machine learning methods (neural networks, radial basis function, decision trees, nearest neighbors), and association rules. Also included are utility functions including random number generators and functions for rank ordering, sorting, mean and sum of squares updates, two-way classification comparison, and save and load models.

Who is it for?

Application developers working in areas such as life sciences, research, finance, and ISVs rely on NAG’s DMC components to enhance performance and significantly reduce development time. Data mining plays an essential part in applications in a range of business activities including:

  • Bio-Informatics
  • Finance
  • Consumer Behavioral Modeling
  • CRM
  • e-Business
  • Fraud Detection
  • Web Analytics
  • Retail

Features & Benefits

Features Benefits
Enhanced data cleaning functions "Cleans" data by imputing missing values, having a detrimental effect on the quality of your analysis.
Advances in outlier identification Identify unusual or extreme-valued data points that will have an undue influence on a fitted model.
Machine learning and pattern recognition functionality From the intuitive analysis obtained from decision trees and nearest neighbors to nonlinear models such as radial basis functions and multi-layer perceptrons, NAG DMC includes a wide range of recent analytical developments.
Specifically designed for large data sets Recognize the potential to create competitive advantage by unlocking the relationships in your data warehouses with multivariate statistical algorithms specifically designed for large data sets by using limited storage and out-of-core solvers.
Easy integration Integrates into a broad range of applications including those developed in Java, C/C++, and .NET, significantly speeding up application development and easily enhancing existing or new applications.
Multiple user interfaces Ideally suited for interfacing with other programming languages such as PERL, Java, C#, and Python. Multiple user interfaces enable quick and easy prototyping, greater control and enhanced performance. You can rely on the results and spend less time redeveloping applications.
Comprehensive documentation DMC is supported through NAG’s thorough documentation including detailed function documents, guidance on which routines to select for particular scenarios, and example calling programs and data.
Available for your computing environments Available for Windows, Mac OS X, Linux, Solaris, and other Unix platforms.
Standards Compliant All functions conform fully to ANSI and to CRISP-DM (cross-industry standard process for data) allowing interoperability with other software.

NAG services

You can get access to the Data Mining Components through a NAG consulting agreement. This gives you access to the entire suite of functions from which you can select the components that you currently need and also allow for future application refinement and extension. You can rely on the proven accuracy and reliability of NAG software to give you the right answers.


Supporting Documentation

Underpinning the quality of all NAG software is our renowned and comprehensive documentation. NAG's Data Mining and Clean Components software is accompanied by thorough documentation, giving you the detailed information you need to help you carry out your work quickly and efficiently.

Available documentation includes:

Essential Introduction (pdf file 152K)

This document describes information fundamental to the successful use of the NAG DMC. It begins with a description of the product and accompanying documentation, describes key issues regarding product use and gives details of NAG’s support facilities.

Users' Guide (pdf file 177K)

This document provides a guide to the functionality available in the NAG DMC. For convenience and clarity, the documentation is divided into sections based on a need to accomplish analytical tasks.

Installer's and Users' Notes

The Installer's Note is essential reading for the NAG Site Contact responsible for installation and maintenance of the product. The Users' Note is essential reading for every user of the product. It provides implementation-specific detail that augments the information provided in the NAG product documentation.

pdf icon Please note: Some documents are presented in Adobe Portable Document Format (PDF) that requires the Adobe Acrobat Reader application. Adobe Acrobat Reader can be downloaded free of charge from the Adobe Web Site at The Adobe Reader allows anyone to view, navigate and print documents in the Adobe Portable Document Format (PDF).

Product Availability

Product Platform Release Precision Comment
the Data Mining Comp
IBM Power4+ AIX64 Release 2.0 Double xlc_r
the Data Mining Comp
Apple Power Mac Release 2.0 Double gnu C
the Data Mining Comp
Intel-32 Windows Release 2.0 Double MSV C/C++ v
the Data Mining Comp
HP Itanium2 HP-UX Release 2.0 Double HP C/C++
the Data Mining Comp
IBM Power AIX Release 2.0 Double xlc v 7
the Data Mining Comp
x86-64 Linux64 Release 2.0 Double gcc 3.3.5
the Data Mining Comp
x86-32 Linux Release 2.0 Double gcc v3.2.2
the Data Mining Comp
Sun SPARC Solaris Release 2.0 Double Workshop 5 C

Distribution: The standard medium for the supply of our products is CD-ROM. However, we are able to offer alternatives if CD-ROM is not suited to the machine on which you intend to run the software. Please check with our Sales Department which alternative medium is available when you place your order.


Website Feedback

If you would like a response from NAG please provide your e-mail address below.

(If you're a human, don't change the following field)
Your first name.
This question is for testing whether you are a human visitor and to prevent automated spam submissions.
Enter the characters shown in the image.