An e-customer behavior model with online analytical mining for internet marketing planning

In the digital market, attracting sufficient online traffic in a business to customer (B2C) Web site is vital to an online business's success. The changing patterns of Internet surfer access to e-commerce sites pose challenges for the Internet marketing teams of online companies. For e-business to grow, a system must be devised to provide customers' preferred traversal patterns from product awareness and exploration to purchase commitment. Such knowledge can be discovered by synthesizing a large volume of Web access data through information compression to produce a view of the frequent access patterns of e-customers. This paper develops constructs for measuring the online movement of e-customers, and uses a mental cognitive model to identify the four important dimensions of e-customer behavior, abstract their behavioral changes by developing a three-phase e-customer behavioral graph, and tests the instrument via a prototype that uses an online analytical mining (OLAM) methodology. The knowledge discovered is expected to foster the development of a marketing plan for B2C Web sites. A prototype with an empirical Web server log file is used to verify the feasibility of the methodology.