Decision-Making Support Software Tools Based on Original Authoring Bayesian Probabilistic Models

Abstract

The article presents programs that implement original approaches to group expert rating estimation and fuzzy inference. They implement probabilistic models based on Bayes’ Formula, previously proposed and published in the works of the authors. In these models, the estimated input data are interpreted as evidence in favor of one or another hypothesis from the set of possible ones, determined by the specifics of the model. All the evidence obtained is, in one way or another, transformed into a set of Bayesian conditional probabilities calculated under the assumption that the corresponding hypothesis is true, and the posterior probability distribution on the set of these hypotheses is used as the output. This distribution is used either directly as a result for decision making, or as a basis for calculating the final result. The features of the software implementation of models on the Java platform are discussed, the advantages of the models, confirmed or identified in the process of software implementation, are noted. The developed programs have a convenient graphical user interface and can be used as decision-making support tools to solve applied problems in the field of expert rating estimation and fuzzy inference.