Abstract: A decision support system, including a decision model, provides an indication, either of itself or in combination with a weighted average of the scores assigned to the decision model factors, of the degree to which the pattern of contribution scores corresponds to a benchmark pattern. This indication, referred to as a matching index, can be calculated according to a class of matching index functions, including those based on regression-correlation and Bayesian pattern matching and cost/loss concepts. In addition, the distribution quality and bias can be indicated by another measure referred to as the distribution quality bias measure which is an indication of how biased such a contribution distribution is, with respect to a benchmark of contributions. The matching index and distribution quality and bias measure can be combined to indicate an overall quality value of match, as opposed to a simple measure of pattern matching or weighted averages.

Abstract: A decision support system, including a decision model, provides an indication, either of itself or in combination with a weighted average of the scores assigned to the decision model factors, of the degree to which the pattern of contribution scores corresponds to a benchmark pattern. This indication, referred to as a matching index, can be calculated according to a class of matching index functions, including those based on regression-correlation and Bayesian pattern matching and cost/loss concepts. The matching index also allows the designation of model factors as `Must Have` or `Must Not Have` factors, and asymmetric functions for special circumstances. The decision support system can be used to assist in the control of a variety of systems and/or processes and/or in the analysis of information, wherever patterns of information may assist in the selection of an alternative from amongst a set of decision alternatives.

Abstract: A method and system for balancing weights in models for decision support systems. When weights in such a model are assigned as local weights, evaluators may obtain non-intuitive results due to biases introduced by variations in the number of child factors of parent factors at a given level. Adjusting weights assigned within the model provides results which are often more intuitive to an evaluator. Two methods of calculating appropriate balancing coefficients to adjust weights are presented.