A Fast Method for Discovering Critical Edge Sequences in E-Commerce Catalogs∗

Web sites allow the collection of vast amounts of navigational data – clickstreams of user traversals through the site. These massive data stores offer the tantalizing possibility of uncovering interesting patterns within the dataset. For e-businesses, always looking for an edge in the hypercompetitive online marketplace, the discovery of Critical Edge Sequences (CESs), which denote frequently traversed sequences in the catalog, is of significant interest. CESs can be used to improve site performance and site management, increase the effectiveness of advertising on the site, and gather additional knowledge of customer behavior patterns on the site. Using web mining strategies to find CESs turns out to be expensive in both space and time. In this paper, we propose an approximate algorithm to compute the most popular traversal sequences between node pairs in a catalog, which are then used to discover CESs. Our method is both fast and space efficient, providing a vast reduction in both the run time and storage requirements, with minimum impact on accuracy. ∗An early version of this work appeared in the ACM Conference on Electronic Commerce, 2001 †Florida International University ‡Walking Stick Solutions, Inc. §Georgia Institute of Technology ¶Indian Institute of Technology, Mumbai