Data Mining - Professional SQL Server Analysis Services 2005 with MDX - page 733

saves marketing money for the companies and they have a better probability
of making sales.
The following steps show you how to solve the targeted mailing type problem
by creating a relational mining model on top of the vTargetMail view in the Ad-
venture Works DW database. To create a relational mining model, you first
need a data source view containing the table(s) on top of which you want to
build a mining model.
1. Create a new Analysis Services project DM2005Tutorial. Create a
data source to the Adventure Works DW relational database
2. Create a DSV that includes the vTargetMail view in the Adventure
Works DW.
◦ The vTargetMail is a view that retrieves information from the
server tables in the Adventure Works DW database. The
vTargetMail view contains information about customers who
buy bicycles. Based on the information in the view, you can
identify potential customers who are likely to buy bicycles.
The vTargetMail view has been specifically designed to con-
tain patterns that can be identified by the data mining al-
gorithms. As the name of the view indicates, vTargetMail is
used to demonstrate the usefulness of the data mining
where the customers can be categorized based on their at-
tributes, and targeted mails with discounts or attractions can
be sent only to customers who are likely to buy bicycles.
3. Similar to the wizard that helped you to create cubes and dimen-
sions, there is a wizard to create data mining structures. To create a
relational mining model right-click the Mining Structures folder in the
solution explorer and select New Mining Structures as shown in Fig-
ure 14-2 .