(AI Studio Core)
Synopsis
This operator applies the given association rules on an ExampleSet.Description
This operator creates a new confidence attribute for each item occurring in at least one conclusion of an association rule. Then it checks for each example and for each rule, if the example fulfills the premise of the rule, which it does, if it covers all items in the premise. An example covers an item, if the attribute representing the item contains the positive value. If the check is positive, a confidence value for each item in the conclusion is derived. Which value is used, depends on the selected confidence aggregation method. There are two types: The binary choice will set a 1, for any item contained inside a fulfilled rule's conclusion. This is independent of how confident the rule was. Any aggregation choice will select the maximum of the previous and the new value of the selected confidence function.
Association rules are if/then statements that help uncover relationships between seemingly unrelated data. An example of an association rule would be "If a customer buys eggs, he is 80% likely to also purchase milk." An association rule has two parts, an antecedent (if) and a consequent (then). An antecedent or premise is an item (or itemset) found in the data. A consequent or conclusion is an item (or itemset) that is found in combination with the antecedent.
Association Rules can be created by using the Create Association Rules operator. Association rules are created by analyzing data for frequent if/then patterns and using the criteria support and confidence to identify the most important relationships. Support is an indication of how frequently the items appear in the database. Confidence indicates the number of times the if/then statements have been found to be true. The frequent if/then patterns are mined using the operators like the FP-Growth operator. The Create Association Rules operator takes these frequent itemsets and generates association rules.
Such information can be used as the basis for decisions about marketing activities such as, e.g., promotional pricing or product placements. In addition to the above example from market basket analysis association rules are employed today in many application areas including Web usage mining, intrusion detection and bioinformatics.
Input
example set (Data table)This input port expects an ExampleSet. It is output of the Subprocess operator in the attached Example Process.
association rules (Association Rules)This input port expects association rules.
Output
- example set (Data table)
The association rules are applied and the resultant ExampleSet is output of this port.
Parameters
- confidence aggregation methodThis parameter selects the method for aggregation of the confidence on the items in each fulfilled conclusion.
- positive valueThis parameter determines, which value of the binominal attributes is treated as positive. Attributes with that value are considered as part of a transaction. If left blank, the ExampleSet determines which value to use.
Tutorial Processes
Applying association rules
This Example Process starts with the Subprocess operator which provides an ExampleSet and Association Rules. A breakpoint is inserted here so that you can view the ExampleSet and the Association Rules. This Example Process deals with the application of these rules. If you want to know how these association rules were created, please study the Example Process of the Create Association Rules operator. The ExampleSet and Association Rules are provided as input to the Apply Association Rules operator. All parameters of the Apply Association Rules operator are used with default values. The resultant ExampleSet can be viewed in the Results Workspace. You can see that this operator has created several confidence attributes in the ExampleSet. The explanation of these confidence attributes is given in the description of this operator.
