We will introduce a knowledge discovery system developed on the World Wide Web platform in this paper. Its algorithm is based on Fuzzy Inductive Learning Method (FILM), which can segment consumers' behavior from a set of customer data with noises. In a visualization way, the system will present the acquired knowledge as a set of IF-THEN rules that can be run on top of an expert system. Moreover, the system will provide advices in response to a user's request through the network and a friendly user interface. At last, we evaluate the function of the system by training it with a transaction database provided by a local automobile dealer.