Page 175 - DCAP606_BUSINESS_INTELLIGENCE

Business Intelligence

Notes

Task Find out the difference between Mining Model Viewer and Mining Accuracy Chart
Tab?

12.2 Mining Structure

The mining structure defines the data from which mining models are constructed: it specifies the
source data outlook, the number and kind of columns, and an optional partition into training
and testing groups. A single mining structure can support multiple mining models that share
the identical domain. The following diagram shows the connection of the data mining structure
to the data source, and to its constituent data mining models.

Figure 12.1: Connection of the Data Mining Structure to the Data Source

Source: http://i.technet.microsoft.com/dynimg/IC13488.gif
The mining structure in the Figure 12.1 is based on a data source that comprises multiple tables
or views, connected on the CustomerID field. One table contains data about customers, such as
the region, age, earnings and gender, while the associated nested table comprises multiple rows
of additional data about each customer, such as goods the customer has bought. The Figure 12.1
shows that multiple models can be constructed on one mining structure, and that the models can
use different columns from the structure.

Here:
Model 1 uses CustomerID, Income, Age, Region, and filters the data on Region.
Model 2 uses CustomerID, Income, Age, Region and filters the data on Age.
Model 3 uses CustomerID, Age, Gender, and the nested table, with no filter.

As the models use different columns for input, and because two of the models also restrict the
data that is used in the model by applying a filter, the models might have very different results
even though they are based on the same data.

170 LOVELY PROFESSIONAL UNIVERSITY