Integrating web mining and neural network for personalized e-commerce automatic service

Electronic commerce (EC) has become a trend in the world nowadays. However, most researches neglect a fundamental issue – the user’s product-specific knowledge on which the useful intelligent systems are based. This research employs the user’s product-specific knowledge and mine his/her interior desire on appropriate target products as a part of personalization process to construct the overall EC strategy for businesses. aper illustrates a novel web usage mining approach, based on the sequence mining technique applied to user’s navigation behaviour, to discover patterns in the navigation of websites. Three critical contributions are made in this paper: (1) using the footstep graph to visualize the user’s click-stream data and any interesting pattern can be detected more easily and quickly; (2) illustrating a novel sequence mining approach to identify pre-designated user navigation patterns automatically and integrates back-propagation network (BPN) model smoothly; and (3) applying the empirical research to indicate that the proposed approach can predict and categorize the users’ navigation behaviour with high accuracy.