Machine learning-based intelligent recommendation in virtual mall

The prosperity of e-commerce has changed the traditional trading behaviors and more and more people are willing to conduct Internet shopping. However, the exponentially increasing information provided by the Internet enterprises causes the problem of searching a lot of information hi which customers are not interested. This would annoy the customers and finally lead them to quit shopping. To solve this problem, our paper builds a personalized products selection system in virtual mall to retrieve product information that the customers really demand. In order to realize personalized products selection, some concepts and techniques about machine learning such as rough set, fuzzy set, case-base reasoning (CBR) is applied to our system. On the other hand, to achieve better realistic and human-like behavior, a virtual reality modeling language (VRML) 97-based user interface is developed to permit users to navigate around the virtual mall. A 3D graphical representation of the participants (avatar) is used to raise user acceptance and usability by providing a more natural interaction with Internet.