A new approach to the rule-base evidential reasoning: Stock trading expert system application

The synthesis of fuzzy logic and methods of the Dempster–Shafer theory (the so-called rule-base evidential reasoning) is proved to be a powerful tool for building expert and decision making systems. Nevertheless, there are two limitations of such approaches that reduce their ability to deal with uncertainties the decision makers often meet in practice. The first limitation is that in the framework of known approaches to the rule-base evidential reasoning, a degree of belief can be assigned only to a particular hypothesis, not to a group of them, whereas an assignment of a belief mass to a group of events is a key principle of the Dempster–Shafer theory. The second limitation is concerned with the observation that in many real-world decision problems we deal with different sources of evidence and the combination of them is needed. The known methods for the rule-base evidential reasoning do not provide a technique for the combination of evidence from different sources. In the current paper, a new approach free of these limitations is proposed. The advantages of this approach are demonstrated using simple numerical examples and the developed stock trading expert system optimized and tested on the real data from Warsaw Stock Exchange.