BARD: A structured method and application for collaboratively building Bayesian networks to support human reasoning and decisions

In many complex real-world situations, problem solving and decision making require effective reasoning about causation and uncertainty. However, human reasoning in these cases is notoriously prone to confusion and error [Kahneman et al., 1982]. One way to support better reasoning is to employ Bayesian networks (BNs) [Pearl, 1988] to model and represent uncertain situations clearly for the user, and make complex calculations quickly and accurately on demand. BNs have been deployed for this purpose in diverse domains such as medicine, education, engineering, surveillance, the law, weather forecasting, and the environment.