Construction of a classifier with prior domain knowledge formalised as Bayesian network

Efficient combination of prior domain knowledge and examples are essential to classification. In this paper, a pragmatic methodology is suggested which uses prior domain knowledge formalised as a Bayesian network to enhance various steps in the process of the construction of a classifier. It is shown that the Bayesian network methodology is not only an alternative to the "black box approach" of classifier construction, but it provides a general supplementary tool.