Home

In conventional data mining field, association rules, introduced in [Agrawal 1993], provide a useful mechanism for discovering correlations among items belonging to customer transactions in a market basket database. An association rule has the form X皺Y, where X and Y are sets of items or itemsets. Let the support of an itemset X be the fraction of database transactions that contain X. The support of a rule of the form X皺Y is then the same as the support of X盎Y, while its confidence is the ration of the supports of X 盎 Y and X. The association rules problem is that of computing all association rules that satisfy user-specified minimum support and minimum confidence constraints.

In the context of Web mining, this problem amounts to discovering the correlations among references to various files available on the server by a given client. Each transaction is comprised of a set of URLs (path) accessed by a client in one visit to the server.  For example, using association rule discovery techniques we can find correlation such as the following:

• 40% of clients who accessed the Web page with URL /company/product1, also accessed  /company/product2;

• 30% of clients who accessed /company/special, placed an online order in /company/product1.

Discovery of such rules for organizations engaged in electronic commerce can help in the development of effective marketing strategies. But, in addition, association rules discovered from Web access logs can give an indication of how to best organize the organization's Web space. Association rule is a basic and important way to analyze user navigation pattern.