Data Structure Examples

Association Discovery Data

Here is an example of association discovery data.

[Output window showing Data for Association Discovery.]

This output contains the following variables:

CUST_NUM, customer number, an ID (identification) variable.
LASTNAME, the customer's last name.
FIRSTNAM, the customer's first name.
PRODUCT, a nominal (class) variable that contains the product purchased.

For an association discovery analysis (basket analysis) that uses PRODUCT as the target variable and CUST_NUM as the ID (identification) variable, the Variables tab of the Input Data Source node would appear as follows:

[Variables tab of the Input Data Source window]

Note: The values in the Name and Type columns are dimmed and unavailable because they are protected fields. [cautionend]

The process flow diagram appears as follows:

[Process flow diagram with Input Data Source connected to Association node]

You can also use the Association node to perform sequence discovery. Sequence discovery goes one step further than association discovery by taking into account the ordering of the relationship among items. For example sequence discovery asks, "Of those customers who purchase a new computer, 25% of them will purchase a laser printer in the next quarter." To perform sequence discovery, you must also assign a sequence model role to a time stamp variable. For information about sequence discovery, see the online documentation for the Association node.

Top of Page