Expanding the Knowledge Base for more Effective Data Mining

Traditionally, data mining, as part of the knowledge discovery process, relies solely on the information contained in the database to generate patterns. Recently, there has been some recognition in the field that expanding the knowledge passed to the pattern generation phase by including other domain knowledge, may have beneficial effects of the interestingness and actionability of the resulting patterns. In this paper, we present a new knowledge discovery method that uses additional decision rules and the analytic hierarchy process (AHP) to conceptualize and structure the domain, thus capturing a broader notion of domain knowledge upon which data mining can be applied. Based on design science guidelines, we design, develop and implement our method within the domain of a brain trauma intensive care unit.