Association Model Viewer

This selection displays a successfully built association model.

Menus

The following menus appear when the model is displayed in a new window:

Tabs

The model viewer has the following tabs:

Build Settings

This tab displays the Type of the model (Association), the Function settings used to build the model, and the Attributes used in model build.

Oracle Data Mining 11g models can be built using Automatic Data Preparation (ADP). If the model was built using ADP, then Automatic Data Preparation has the value yes.

The following algorithm settings are displayed:

For more information about the algorithm settings, see Settings for Apriori Algorithm.

The attributes used to build the model are displayed in the Attributes grid; the following information is displayed for each attribute:

To save the attributes information as a text file, click the Save As icon (a yellow arrow above a graphic of a page) above the Attributes grid.

Rules

To see the rules, click the Rules tab.

The Total Rules, the number of rules, is displayed.

Zero Rules

If Total Rules is 0, the model found no rules. To build a model that finds rules, modify the build options and rebuild the model. First try decreasing Minimum Support; if that doesn't work, decrease Minimum Confidence.

View Rules

If Total Rules is greater than 0, click Get Rules. A dialog appears to let you pick the rules to display. You must specify antecedents and consequents for the rule. You can specify rules between all attributes and/or specific attributes. You can change the default fetch size of 100 rules. You can specify minimum confidence and support. You can specify how the rules are to be sorted. The browser then gets the specified rules and displays the number of rules specified by the fetch size. If there are a large number of rules, this operation may take a while.

To get a different set of rules, click Get Rules again and specify new criteria for rules.

The rules are displayed in the Rules grid. For each rule the following are displayed: Rule id, If (condition), Then (association), Confidence (%), and Support (%).

To view a detailed display of a rule, select the rule; the browser displays the details in the Rule Detail area.

To sort the rules according to Rule id, Confidence, or Support, click the appropriate column heading. The browser sorts all of the rules in the specified way and displays the number of rules specified by fetch size. If there are a large number of rules, this operation may take a while.

To save the rules to a file, click the Save As icon (a yellow arrow above a graphic of a page) above the Rules grid.

Rules Interpretation

Rules displayed by Oracle Data Miner use the notation =1 to mean "is present in the basket." For example, the rule IF BasketBall=1 AND Tennis Balls Outdoors=1 THEN Athletic Socks=1 means that a basket that contains one or more basket balls and one or more outdoors tennis balls is likely to contain one or more pairs of athletic socks.

Confidence and Support

Oracle Data Mining calculates the following items for each association rule:

Support and confidence can be used to rank the rules and, therefore, the predictions.

Task

This tab describes the task used to build the model. It shows when the task ran, what input was used, and what output was created.