Association analysis is the discovery of association rules. Market basket analysis has been a strong motivation for the development of association analysis. Association rules specify correlations between frequent item sets (sets of items, such as bread and butter, which are often found together in a transaction, for example, a market basket).
The task of association analysis is typically performed in two steps. First, all frequent item sets are found, where an item set is frequent if it appears in at least a given percentage (called support) of all transactions. Next, association rules are found of the form X! Y, where X and Y are frequent item sets and the confidence of the rule (the percentage of transactions containing X that also contain Y) passes a given threshold.
Was this article helpful?