This is a limited free preview of this book. Please buy full access.
method and applies it to a market segmentation problem. At the same time, comparisons are made between the proposed method and commonly used methods from both data mining and marketing research. The results show that the proposed method performs very well. The second essay focuses on a specific marketing problem: the relationship between free shipping promotions and Internet shopping behavior. It uses original analytical models and empirical methods from both marketing and data mining research to address the problem.
Each essay is independently evaluated on different data sets originating from the Web. Researchers and practitioners often struggle with how to best to leverage clickstream data given various idiosyncratic challenges. The use of real Web clickstream data in this research adds another dimension that will be of significant interest.
Building on the notion that observable customer transactions are generated by latent behavioral traits, the first essay investigates the use of a novel pattern-based clustering approach to grouping customer transactions. An objective function is defined and maximized in order to achieve a good clustering of customer transactions. An algorithm groups customer transactions such that patterns generated from each cluster are homogeneous within but heterogeneous between cluster groups. Experimental results from user-centric Web usage data demonstrate that the proposed approach generates a highly effective clustering of transactions. These behavior-based clusters are then used to build more accurate predictive models. A notable strength of the approach is the ability to label the clusters with behavioral patterns and describe the differences between clusters with contrasting behavioral patterns. An important contribution of this first essay is the development of this novel clustering approach that is based on the concept of pattern difference and similarity.
The main contribution of the second essay is that it studies an important Internet marketing problem that has not been well researched. It analyzes the impact of different free-shipping schedules on the shopping