Data mining model based on rough set theory

On purpose of improving the solution and research in reasoning and decision making problems when the information in hand is not sufficient, a data mining model based on rough set theory is presented. From the initial decision system defined by the primitive data, a series of subsystems with various reductive levels are created. For each sub-system, the rule sets with respective belief degrees are induced and saved. When applying the model to reasoning and decision analysis, one can match the information of the given object to the rule sets of relative modes, and then draw the conclusion by using some kind of evaluation algorithm. A simple example on how to create and apply the model is given. The presented model can be applied conveniently by selecting suitable sub-systems in accordance with the given information and computing the best decision from the rules in those subsystems.