Abstract
In this paper, we develop pattern mining and prediction techniques that explore the correlation between the moving behavior and purchasing transactions of mobile users to explore potential M-Commerce features. The MCE framework consists of three major components: The first component is Similarity Inference Model (SIM) for measuring the similarities among stores and items. The second component is Personal Mobile Commerce Pattern Mine (PMCP-Mine) algorithm for efficient discovery of mobile users’ Personal Mobile Commerce Patterns (PMCPs); and the last component is Mobile Commerce Behavior Predictor (MCBP) for prediction of possible mobile user behaviors. Based on the predicted patterns we recommend stores and items previously unknown to a user