A new approach to risk management using soft information

We discuss a new approach to aid in decision making in risky situations. This approach is based on the use of a fuzzy rule based formulation to valuate a decision maker's preferences. This allows us to model the responsible agents decision function, their attitude with respect to different uncertain risky situations. An important aspect of risky decision-making is the modeling of the uncertainty associated with an alternative. We refer to this as an alternative's uncertainty profile. In the real world this kind of information can be ill defined and imprecise. We discuss the role of perception based granular probability distributions as a means of modeling the uncertainty profiles of the alternatives. We shown how this can be used to modeling imprecision in our knowledge about the uncertainty associated with an alternative. We provide the necessary formalisms to allow for the evaluation of an alternative using the rule-based description of preferences and granular description of an alternatives uncertainty profile.