Most existing data mining approaches to e-commerce recommendation are past data model-based in the sense that they first build a preference model from a past dataset and then apply the model to current customer situations. Such approaches are not suitable for applications where fresh data should be collected instantly since it reflects changes to customer preferences over some products. This paper targets those e-commerce environments in which knowledge of customer preferences may change frequently. But due to the very large size of past datasets the preference models cannot be updated instantly in response to the changes. We present an approach to making real time online recommendations based on an up-to-moment dataset which includes not only a gigantic past dataset but the most recent data that may be collected just moments ago.
CITATION STYLE
Shen, Y. D., Yang, Q., Zhang, Z., & Lu, H. (2003). Mining the customer’s Up-to-moment preferences for E-commerce recommendation. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 2637, pp. 166–177). Springer Verlag. https://doi.org/10.1007/3-540-36175-8_17
Mendeley helps you to discover research relevant for your work.