An applied approach to numerically imprecise decision making

Despite the fact that unguided decision making might lead to inefficient and nonoptimal decisions, decisions made at organizational levels seldom utilise decisionanalytical tools. Several gaps between the decision-makers and the computer baseddecision tools exist, and a main problem in managerial decision-making involves the lack of information and precise objective data, i.e. uncertainty and imprecision may be inherent in the decision situation. We believe that this problem might be overcome by providing computer based decision tools capable of handling the uncertainty inherent in real-life decision-making. At present, nearly all decision analytic software is only able to handle precise input, and no known software is capable of handling full scale imprecision, i.e. imprecise probabilities, values and weights, in the form of interval and comparative statements. There are, however, some theories which are able to handle some kind of uncertainty, and which deal with computational and implementational issues, but if they are never actually operationalised, they are of little real use for a decision-maker. Therefore, a natural question is how a reasonable decision analytical framework can be built based on prevailing interval methods, thus dealing with the problems of uncertain and imprecise input? Further, will the interval approach actually prove useful? The framework presented herein handles theoretical foundations for, and implementations of, imprecise multi-level trees, multi-criteria, risk analysis, together with several different evaluation options. The framework supports interval probabilities, values, and criteria weights, as well as comparative statements, also allowing for mixing probabilistic and multi-criteria decisions. The framework has also been field tested in a number of studies, proving the usefulness of the interval approach