Abstract-The idea that context is important when predicting customer behavior has been maintained by scholars in marketing and data mining. However, no systematic study measuring how much the contextual information really matters in building customer models in personalization applications has been done before. In this paper, we study how important the contextual information is when predicting customer behavior and how to use it when building customer models. It is done by conducting an empirical study across a wide range of experimental conditions. The experimental results show that context does matter when modeling the behavior of individual customers and that it is possible to infer the context from the existing data with reasonable accuracy in certain cases. It is also shown that significant performance improvements can be achieved if the context is "cleverly" modeled, as described in this paper. These findings have significant implications for data miners and marketers. They show that contextual information does matter in personalization and companies have different opportunities to both make context valuable for improving predictive performance of customers' behavior and decreasing the costs of gathering contextual information.
In e-commerce applications, no systematic research has been provided to evaluate if the use of a detailed and rich contextual representation improves the user modeling predictive performances. An underestimated issue is also evaluating if context could be inferred by existing customer data off-line, in spite of getting the customer involved on-line in the gathering process. In this paper, we address those problems, defining context as "the intent of" a customer purchase. To this aim, we collected data containing rich contextual information, hierarchically structured, by developing a special-purpose browser. The experimental results show that the finer the granularity of contextual information the better is the modeling of customers' behavior. Representing the context in a hierarchical structure is a necessary condition, for inferring the context off-line, but it's not a sufficient one.
In e-commerce, where the search costs are low and the competition is just a mouse click away, it is crucial to accurately predict customer purchasing behavior in order to offer more targeted and personalized products and services. Recent research has demonstrated that including the context in which a transaction occurs in customer behavior models improves their predictive performance, especially when studying individual customer behavior. However, several practical and managerial issues can arise, thus driving companies to focus on segments rather than on individuals. The main contribution of this work lies in presenting a conceptual framework to incorporating context when building predictive models of market segments, and in comparing different approaches, across a wide range of experimental conditions. Our experiments show that the most accurate approach is not the most efficient from a managerial perspective. Our findings provide insights of how companies can exploit context at best to support marketing decisionmaking.
The growing complexity and variability characterizing markets have induced scholars and marketers to propose new segmentation approaches. Recent research has shown that including the context in which a transaction occurs in customer behavior models, improves the ability of predicting their behavior. However, no systematic research has studied whether contextual information really matters in market segmentation. To this aim we conducted an empirical study in an e-commerce application across a wide range of experimental conditions. The results show that context strongly affects the composition of segments. Moreover, including context in the segmentation approach can improve both the homogeneity of segments and the ability of predicting customer behavior. Finally in some experimental conditions, the finer contextual information is, the better segmentation results are. Some managerial implications related to the benefits and complexity of a contextual segmentation are discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.