Risk-management by probability-based patterns in data-mining

Abstract

In this paper a new method is suggested for risk management by the designed patterns in data-mining. These patterns are designed using probability rules in decision trees and are cared to be valid, novel, useful and understandable. Considering a set of functions, the system reaches to a good pattern or better objectives. By using the suggested method the direction of the functionality route in the system can be controlled and systems use them in the best planning for special objectives.