This paper presents a model for identifying general intentions of consumers visiting a retail website. When visiting a transactional website, consumers have various intentions such as browsing (i.e., no purchase intention), purchasing a product in the near future, or purchasing a particular product during their current visit. By predicting these intentions early in the visit, online merchants could personalize their offer to better fulfill the needs of consumers. We propose a simple model which enables classifying visitors according to their intentions after only four traversals (clicks). The model is based solely on navigation patterns which can be automatically extracted from clickstream. The results are presented and extensions of the model are proposed.
Kalczynski, Pawel; Senecal, Ph.D., Sylvain; and Fredette, Marc, "Dynamic Prediction of retail Website Visitors' Intentions" (2008). ICEB 2008 Proceedings (Hawaii, Waikoloa, Big Island). 52.