The hierarchical knowledge representation for automated reasoning

In the paper the study of knowledge hierarchical representation for automated reasoning is presented. The hierarchical knowledge representation is proposed for predictive modeling purpose. It is improved an effective automated reasoning structure for data set analyzes and making decisions based on complex relations between this data. It is important to emphasize that it is not considered a - priori knowledge concerning data structure, therefore the approach automatically discovers particular constraints between data. It provides a technique of the verification the hierarchical knowledge representation building process that can be useful for the model justification. The presented numerical experiment shows an advantage of proposed approach. It is assumed that the presented automated reasoning can be used for classification purpose where there is a difficulty of proper classifier choice.