association rules
A predictive analytics technique that analyzes data for frequent If…Then patterns and calculates support and confidence criteria that identify the most important relationships. Support indicates how frequently the items appear in the database. Confidence indicates the number of times the If…Then relationships evaluate true.
An association rule has two parts, an antecedent and a consequent. The antecedent represents one or multiple data items. The consequent represents an item found in combination with the antecedent. An association rule returns a lift and a leverage value that measure how well the rule predicts the consequent.
Related terms
antecedent, Association Rules, confidence, consequent, lift, leverage, predictive analytics, support

Additional Links:

Copyright Actuate Corporation 2013 BIRT Analytics 4.2