Building and Using Data Mining Models

Data mining, an exciting feature introduced as part of Microsoft® SQL Server™ 2000 Analysis Services, provides new tools for decision analysis by discovering patterns and rules in data and using them for predictive analysis, using industry standard data mining algorithms.

The primary mechanism for data mining is the data mining model, an abstract object that stores data mining information in a series of schema rowsets. Data mining models are easily accessible with a variety of tools. You can use the Mining Model Wizard to create data mining models, and you can use Data Mining Model Browser to display data mining model content in a graphical format.

You can also create, train, and use data mining models programmatically using OLE DB for Data Mining, an extension to the OLE DB specification that supports data mining functionality.

Data mining models can be used to perform sophisticated decision analysis on large amounts of data, whether relational or OLAP, and with a variety of algorithms. The following topics help you through the steps needed to create, train, and apply a data mining model, as well as view the content of a trained data mining model. Advanced operations, such as using mining model roles to provide security for a data mining model, are also covered.