Bayesian network inference with qualitative expert knowledge for group decision making

摘要

In this paper, we propose a practical framework and a methodology for transforming final group decision making statements or expert knowledge into a set of qualitative statements and probability inequality constraints for inference in a Bayesian Network. First we present several techniques in the decision process to produce a group preference ranking and a final group solution. Second, we describe a detailed method to transform the final group solution into a set of qualitative statements and an “a priori” distribution for Bayesian probabilistic models. The decision-making assumptions and the mathematical equation for Bayesian inference are derived based on data and knowledge obtained from experts. We also propose a simplified method for constructing the “a priori” model distribution. Each statement obtained from the group's solution is used to constrain the model space to the subspace which is consistent with the statement provided. Finally, we present qualitative knowledge models and then show a full formalism of how to translate a set of qualitative statements into probability inequality constraints.